Analogical Inference for Multi-Relational Embeddings
|
|
- Rosemary Briggs
- 5 years ago
- Views:
Transcription
1 Analogical Inference for Multi-Relational Embeddings Hanxiao Liu, Yuexin Wu, Yiming Yang Carnegie Mellon University August 8, 2017 nalogical Inference for Multi-Relational Embeddings 1 / 19
2 Task Description Multi-Relational Embeddings: Finding latent representations of entities and relations. Useful for knowledge base completion (by discovering missing facts), etc. Novel Contribution: Instead of tradition rule-based AI, we impose analogical structures in the learning of entity/relation embedding. nalogical Inference for Multi-Relational Embeddings 2 / 19
3 Why Analogy? (a toy example) nucleus surrounded by electrons scale down attract scale down made of sun surrounded by planets charge attract made of scale down mass Figure: Solar System (blue) v.s. Atomic System (red). Knowing the relational structure in one system will help us to understand the other system by analogy. Analogical Inference for Multi-Relational Embeddings 3 / 19
4 Basic Formulation Denote by vector v e the embedding of entity e. Denote by matrix W r in the embedding of relation r. Assume all valid subject-relation-object (s,r,o) triples approximately satisfy v s W r v o (1) Define the scoring function of any (s,r,o) triple as: φ(s, r, o) = v s W r, v o = v s W r v o (2) Analogical Inference for Multi-Relational Embeddings 4 / 19
5 Real Normal Matrices as Desirable The family of matrices satisfying: Wr W r = W r Wr (3) Special cases: 1. Symmetric Matrices φ(s, r, o) = φ(o, r, s). E.g. is identical. 2. Skew-symmetric Matrices φ(s, r, o) = φ(o, r, s). E.g. is parent of. 3. Orthogonal Matrices Useful if r is a bijection (one-to-one mapping). Analogical Inference for Multi-Relational Embeddings 5 / 19
6 Commutative Matrices as Necessary Observation: Analogical structures often imply parallelograms, e.g., man is to king as woman is to queen Or, in an abstract notion: a is to b as c is to d a r r c b r r d Given the parallelogram, if we know a r b and a r c, then c r d and b r d can be inferred by symmetry. nalogical Inference for Multi-Relational Embeddings 6 / 19
7 Commutative Matrices as Necessary (cont d) Mathematically, the necessary condition for having an analogical structure is the commutativity of relations: r r = r r (4) a r r c b r r d Equivalently, we want the following constraint: W r W r = W r W r (5) nalogical Inference for Multi-Relational Embeddings 7 / 19
8 Optimization: Straightforward Formulation Notation: Label y = +1 for positive examples and 1 otherwise; Data distribution D; Loss function l. min E s,r,o,y D l (φ v,w (s, r, o), y) (6) v,w s.t. W r W r = W r W r r (7) W r W r = W r W r r, r (8) (7) follows the definition of normal matrices. (8) is for the communicative property. The OPT is expensive due to (i) W r s are fully dense matrices (ii) large number of equality constraints. nalogical Inference for Multi-Relational Embeddings 8 / 19
9 Optimization: Complexity Reduced Version Solution v, W for the previous OPT can be exactly recovered by solution v, W of the following problem: Most notably, min E s,r,o,y D l (φ v v,w,w (s, r, o), y) (9) We show that any W r must be block-diagonal with the diagonal block sizes bounded by 2. O(m) free parameters in the m m matrix. We now have an unconstrained optimization instead. Efficiently solved using SGD without projection. nalogical Inference for Multi-Relational Embeddings 9 / 19
10 A Unified View of Existing Work We explain the strong empirical performance of DistMult (Yang et al., ICLR 2015) ComplEx (Trouillon et al., ICML 2016) HolE (Nickel et al., AAAI 2016) by showing that they are implicitly imposing analogical structures and are restricted cases of ours. nalogical Inference for Multi-Relational Embeddings 10 / 19
11 Connections to Existing Work Multiplicative Embeddings (DistMult) φ(s, r, o) = v s, v r, v o (10) where v s, v r, v o R m, s, r, o (11) DistMult embeddings of size m can be fully recovered by ANALOGY embeddings of size m. Intuition: v r can be viewed as a diagonal W r def = diag(v r ). Diagonal matrices are always commutative. nalogical Inference for Multi-Relational Embeddings 11 / 19
12 Connections to Existing Work Complex Embeddings (ComplEx) φ(s, r, o) = R ( v s, v r, v o ) (12) where v s, v r, v o C m, s, r, o (13) ComplEx embeddings of size m can be fully recovered by ANALOGY embeddings of size 2m. Intuition: ( there ) exists a bijection between any a + bj C a b and R b a 2 2. Analogical Inference for Multi-Relational Embeddings 12 / 19
13 Connections to Existing Work Holographic Embeddings (HolE) φ(s, r, o) = v r, v s v o (14) where v s, v r, v o R m, s, r, o (15) HolE embeddings can be equivalently obtained via φ(s, r, o) = R ( v s, v r, v o ) (16) where v s, v r, v o FFT(R m ) C m, s, r, o (17) Hence is a restricted case of ComplEx and ANALOGY. Intuition: Circular convolution can be converted into element-wise product after Fourier transform. nalogical Inference for Multi-Relational Embeddings 13 / 19
14 Experiments Implementation Details Use logistic loss: l(φ(s, r, o), y) = log σ(yφ(s, r, o)) (18) Optimization: Asynchronous AdaGrad (HogWild!) For each valid (s, r, o), generate negative examples (s, r, o), (s, r, o), (s, r, o ) by corrupting s, r, o. Evaluation Hits and Mean Reciprocal Rank (MRR) Benchmark datasets FreeBase-15K and WordNet-18. nalogical Inference for Multi-Relational Embeddings 14 / 19
15 Results (filt.) Models WN18 FB15K Unstructured RESCAL NTN SME SE LFM TransH TransE TransR TKRL 73.4 RTransE 76.2 TransD CTransR KG2E STransE DistMult TransSparse PTransE-MUL 77.7 PTransE-RNN 82.2 PTransE-ADD 84.6 NLF (+external data) ComplEx HolE Our ANALOGY Analogical Inference for Multi-Relational Embeddings 15 / 19
16 Results & MRR WN18 FB15K Models MRR (filt.) MRR (raw) (filt.) (filt.) MRR (filt.) MRR (raw) (filt.) (filt.) RESCAL TransE DistMult HolE ComplEx Our ANALOGY Analogical Inference for Multi-Relational Embeddings 16 / 19
17 Scalability The algorithm scales linearly over the embedding size FB15K WN Embedding size FB15K WN Number of threads Figure: CPU run time per epoch (secs) of ANALOGY. Intuition: O(m) for almost-diagonal matrices instead of O(m 2 ) for dense matrices. nalogical Inference for Multi-Relational Embeddings 17 / 19
18 Conclusion Contributions: A new framework that explicitly exploit analogy in a differentiable manner. Fast algorithm of linear scalability. Unified view of several representative works. Future work: Other applications where analogies might be useful (Machine Translation, Image Captioning, etc.). nalogical Inference for Multi-Relational Embeddings 18 / 19
19 Poster #51 Code: Thank You! nalogical Inference for Multi-Relational Embeddings 19 / 19
arxiv: v2 [cs.lg] 6 Jul 2017
made of made of Analogical Inference for Multi-relational Embeddings Hanxiao Liu 1 Yuexin Wu 1 Yiming Yang 1 arxiv:1705.02426v2 [cs.lg] 6 Jul 2017 Abstract Large-scale multi-relational embedding refers
More informationSupplementary Material: Towards Understanding the Geometry of Knowledge Graph Embeddings
Supplementary Material: Towards Understanding the Geometry of Knowledge Graph Embeddings Chandrahas chandrahas@iisc.ac.in Aditya Sharma adityasharma@iisc.ac.in Partha Talukdar ppt@iisc.ac.in 1 Hyperparameters
More informationModeling Topics and Knowledge Bases with Embeddings
Modeling Topics and Knowledge Bases with Embeddings Dat Quoc Nguyen and Mark Johnson Department of Computing Macquarie University Sydney, Australia December 2016 1 / 15 Vector representations/embeddings
More informationParaGraphE: A Library for Parallel Knowledge Graph Embedding
ParaGraphE: A Library for Parallel Knowledge Graph Embedding Xiao-Fan Niu, Wu-Jun Li National Key Laboratory for Novel Software Technology Department of Computer Science and Technology, Nanjing University,
More informationA Convolutional Neural Network-based
A Convolutional Neural Network-based Model for Knowledge Base Completion Dat Quoc Nguyen Joint work with: Dai Quoc Nguyen, Tu Dinh Nguyen and Dinh Phung April 16, 2018 Introduction Word vectors learned
More informationKnowledge Graph Completion with Adaptive Sparse Transfer Matrix
Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence (AAAI-16) Knowledge Graph Completion with Adaptive Sparse Transfer Matrix Guoliang Ji, Kang Liu, Shizhu He, Jun Zhao National Laboratory
More informationInterpretable and Compositional Relation Learning by Joint Training with an Autoencoder
Interpretable and Compositional Relation Learning by Joint Training with an Autoencoder Ryo Takahashi* 1 Ran Tian* 1 Kentaro Inui 1,2 (* equal contribution) 1 Tohoku University 2 RIKEN, Japan Task: Knowledge
More informationKnowledge Graph Embedding with Diversity of Structures
Knowledge Graph Embedding with Diversity of Structures Wen Zhang supervised by Huajun Chen College of Computer Science and Technology Zhejiang University, Hangzhou, China wenzhang2015@zju.edu.cn ABSTRACT
More informationarxiv: v2 [cs.cl] 28 Sep 2015
TransA: An Adaptive Approach for Knowledge Graph Embedding Han Xiao 1, Minlie Huang 1, Hao Yu 1, Xiaoyan Zhu 1 1 Department of Computer Science and Technology, State Key Lab on Intelligent Technology and
More informationLearning Entity and Relation Embeddings for Knowledge Graph Completion
Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence Learning Entity and Relation Embeddings for Knowledge Graph Completion Yankai Lin 1, Zhiyuan Liu 1, Maosong Sun 1,2, Yang Liu
More informationA Translation-Based Knowledge Graph Embedding Preserving Logical Property of Relations
A Translation-Based Knowledge Graph Embedding Preserving Logical Property of Relations Hee-Geun Yoon, Hyun-Je Song, Seong-Bae Park, Se-Young Park School of Computer Science and Engineering Kyungpook National
More information2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media,
2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising
More informationarxiv: v1 [cs.ai] 12 Nov 2018
Differentiating Concepts and Instances for Knowledge Graph Embedding Xin Lv, Lei Hou, Juanzi Li, Zhiyuan Liu Department of Computer Science and Technology, Tsinghua University, China 100084 {lv-x18@mails.,houlei@,lijuanzi@,liuzy@}tsinghua.edu.cn
More informationSTransE: a novel embedding model of entities and relationships in knowledge bases
STransE: a novel embedding model of entities and relationships in knowledge bases Dat Quoc Nguyen 1, Kairit Sirts 1, Lizhen Qu 2 and Mark Johnson 1 1 Department of Computing, Macquarie University, Sydney,
More informationKnowledge Graph Embedding via Dynamic Mapping Matrix
Knowledge Graph Embedding via Dynamic Mapping Matrix Guoliang Ji, Shizhu He, Liheng Xu, Kang Liu and Jun Zhao National Laboratory of Pattern Recognition (NLPR) Institute of Automation Chinese Academy of
More informationLocally Adaptive Translation for Knowledge Graph Embedding
Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence (AAAI-16) Locally Adaptive Translation for Knowledge Graph Embedding Yantao Jia 1, Yuanzhuo Wang 1, Hailun Lin 2, Xiaolong Jin 1,
More informationLearning Multi-Relational Semantics Using Neural-Embedding Models
Learning Multi-Relational Semantics Using Neural-Embedding Models Bishan Yang Cornell University Ithaca, NY, 14850, USA bishan@cs.cornell.edu Wen-tau Yih, Xiaodong He, Jianfeng Gao, Li Deng Microsoft Research
More informationREVISITING KNOWLEDGE BASE EMBEDDING AS TEN-
REVISITING KNOWLEDGE BASE EMBEDDING AS TEN- SOR DECOMPOSITION Anonymous authors Paper under double-blind review ABSTRACT We study the problem of knowledge base KB embedding, which is usually addressed
More informationNeighborhood Mixture Model for Knowledge Base Completion
Neighborhood Mixture Model for Knowledge Base Completion Dat Quoc Nguyen 1, Kairit Sirts 1, Lizhen Qu 2 and Mark Johnson 1 1 Department of Computing, Macquarie University, Sydney, Australia dat.nguyen@students.mq.edu.au,
More informationNeural Tensor Networks with Diagonal Slice Matrices
Neural Tensor Networks with Diagonal Slice Matrices Takahiro Ishihara 1 Katsuhiko Hayashi 2 Hitoshi Manabe 1 Masahi Shimbo 1 Masaaki Nagata 3 1 Nara Institute of Science and Technology 2 Osaka University
More informationTransG : A Generative Model for Knowledge Graph Embedding
TransG : A Generative Model for Knowledge Graph Embedding Han Xiao, Minlie Huang, Xiaoyan Zhu State Key Lab. of Intelligent Technology and Systems National Lab. for Information Science and Technology Dept.
More informationTowards Understanding the Geometry of Knowledge Graph Embeddings
Towards Understanding the Geometry of Knowledge Graph Embeddings Chandrahas Indian Institute of Science chandrahas@iisc.ac.in Aditya Sharma Indian Institute of Science adityasharma@iisc.ac.in Partha Talukdar
More informationLearning to Represent Knowledge Graphs with Gaussian Embedding
Learning to Represent Knowledge Graphs with Gaussian Embedding Shizhu He, Kang Liu, Guoliang Ji and Jun Zhao National Laboratory of Pattern Recognition Institute of Automation, Chinese Academy of Sciences,
More informationData-Dependent Learning of Symmetric/Antisymmetric Relations for Knowledge Base Completion
The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18) Data-Dependent Learning of Symmetric/Antisymmetric Relations for Knowledge Base Completion Hitoshi Manabe Nara Institute of Science
More informationRelation path embedding in knowledge graphs
https://doi.org/10.1007/s00521-018-3384-6 (0456789().,-volV)(0456789().,-volV) ORIGINAL ARTICLE Relation path embedding in knowledge graphs Xixun Lin 1 Yanchun Liang 1,2 Fausto Giunchiglia 3 Xiaoyue Feng
More informationEmbedding-Based Techniques MATRICES, TENSORS, AND NEURAL NETWORKS
Embedding-Based Techniques MATRICES, TENSORS, AND NEURAL NETWORKS Probabilistic Models: Downsides Limitation to Logical Relations Embeddings Representation restricted by manual design Clustering? Assymetric
More informationA Randomized Approach for Crowdsourcing in the Presence of Multiple Views
A Randomized Approach for Crowdsourcing in the Presence of Multiple Views Presenter: Yao Zhou joint work with: Jingrui He - 1 - Roadmap Motivation Proposed framework: M2VW Experimental results Conclusion
More informationModeling Relation Paths for Representation Learning of Knowledge Bases
Modeling Relation Paths for Representation Learning of Knowledge Bases Yankai Lin 1, Zhiyuan Liu 1, Huanbo Luan 1, Maosong Sun 1, Siwei Rao 2, Song Liu 2 1 Department of Computer Science and Technology,
More informationModeling Relation Paths for Representation Learning of Knowledge Bases
Modeling Relation Paths for Representation Learning of Knowledge Bases Yankai Lin 1, Zhiyuan Liu 1, Huanbo Luan 1, Maosong Sun 1, Siwei Rao 2, Song Liu 2 1 Department of Computer Science and Technology,
More informationTransT: Type-based Multiple Embedding Representations for Knowledge Graph Completion
TransT: Type-based Multiple Embedding Representations for Knowledge Graph Completion Shiheng Ma 1, Jianhui Ding 1, Weijia Jia 1, Kun Wang 12, Minyi Guo 1 1 Shanghai Jiao Tong University, Shanghai 200240,
More informationCombining Two And Three-Way Embeddings Models for Link Prediction in Knowledge Bases
Journal of Artificial Intelligence Research 1 (2015) 1-15 Submitted 6/91; published 9/91 Combining Two And Three-Way Embeddings Models for Link Prediction in Knowledge Bases Alberto García-Durán alberto.garcia-duran@utc.fr
More informationA Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network
A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network Dai Quoc Nguyen 1, Tu Dinh Nguyen 1, Dat Quoc Nguyen 2, Dinh Phung 1 1 Deakin University, Geelong, Australia,
More informationLearning Embedding Representations for Knowledge Inference on Imperfect and Incomplete Repositories
Learning Embedding Representations for Knowledge Inference on Imperfect and Incomplete Repositories Miao Fan, Qiang Zhou and Thomas Fang Zheng CSLT, Division of Technical Innovation and Development, Tsinghua
More informationMining Inference Formulas by Goal-Directed Random Walks
Mining Inference Formulas by Goal-Directed Random Walks Zhuoyu Wei 1,2, Jun Zhao 1,2 and Kang Liu 1 1 National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing,
More informationNormalization Techniques in Training of Deep Neural Networks
Normalization Techniques in Training of Deep Neural Networks Lei Huang ( 黄雷 ) State Key Laboratory of Software Development Environment, Beihang University Mail:huanglei@nlsde.buaa.edu.cn August 17 th,
More informationImplicit ReasoNet: Modeling Large-Scale Structured Relationships with Shared Memory
Implicit ReasoNet: Modeling Large-Scale Structured Relationships with Shared Memory Yelong Shen, Po-Sen Huang, Ming-Wei Chang, Jianfeng Gao Microsoft Research, Redmond, WA, USA {yeshen,pshuang,minchang,jfgao}@microsoft.com
More informationCME323 Distributed Algorithms and Optimization. GloVe on Spark. Alex Adamson SUNet ID: aadamson. June 6, 2016
GloVe on Spark Alex Adamson SUNet ID: aadamson June 6, 2016 Introduction Pennington et al. proposes a novel word representation algorithm called GloVe (Global Vectors for Word Representation) that synthesizes
More informationWeb-Mining Agents. Multi-Relational Latent Semantic Analysis. Prof. Dr. Ralf Möller Universität zu Lübeck Institut für Informationssysteme
Web-Mining Agents Multi-Relational Latent Semantic Analysis Prof. Dr. Ralf Möller Universität zu Lübeck Institut für Informationssysteme Tanya Braun (Übungen) Acknowledgements Slides by: Scott Wen-tau
More informationType-Sensitive Knowledge Base Inference Without Explicit Type Supervision
Type-Sensitive Knowledge Base Inference Without Explicit Type Supervision Prachi Jain* 1 and Pankaj Kumar* 1 and Mausam 1 and Soumen Chakrabarti 2 1 Indian Institute of Technology, Delhi {p6.jain, k97.pankaj}@gmail.com,
More informationLearning Multi-Relational Semantics Using Neural-Embedding Models
Learning Multi-Relational Semantics Using Neural-Embedding Models Bishan Yang Cornell University Ithaca, NY, 14850, USA bishan@cs.cornell.edu Wen-tau Yih, Xiaodong He, Jianfeng Gao, Li Deng Microsoft Research
More informationComplex Embeddings for Simple Link Prediction
Théo Trouillon 1,2 THEO.TROUILLON@XRCE.XEROX.COM Johannes Welbl 3 J.WELBL@CS.UCL.AC.UK Sebastian Riedel 3 S.RIEDEL@CS.UCL.AC.UK Éric Gaussier 2 ERIC.GAUSSIER@IMAG.FR Guillaume Bouchard 3 G.BOUCHARD@CS.UCL.AC.UK
More informationA fast and simple algorithm for training neural probabilistic language models
A fast and simple algorithm for training neural probabilistic language models Andriy Mnih Joint work with Yee Whye Teh Gatsby Computational Neuroscience Unit University College London 25 January 2013 1
More informationarxiv: v2 [cs.cl] 3 May 2017
An Interpretable Knowledge Transfer Model for Knowledge Base Completion Qizhe Xie, Xuezhe Ma, Zihang Dai, Eduard Hovy Language Technologies Institute Carnegie Mellon University Pittsburgh, PA 15213, USA
More informationLecture 21: Spectral Learning for Graphical Models
10-708: Probabilistic Graphical Models 10-708, Spring 2016 Lecture 21: Spectral Learning for Graphical Models Lecturer: Eric P. Xing Scribes: Maruan Al-Shedivat, Wei-Cheng Chang, Frederick Liu 1 Motivation
More informationSemantics with Dense Vectors. Reference: D. Jurafsky and J. Martin, Speech and Language Processing
Semantics with Dense Vectors Reference: D. Jurafsky and J. Martin, Speech and Language Processing 1 Semantics with Dense Vectors We saw how to represent a word as a sparse vector with dimensions corresponding
More informationarxiv: v4 [cs.cl] 24 Feb 2017
arxiv:1611.07232v4 [cs.cl] 24 Feb 2017 Compositional Learning of Relation Path Embedding for Knowledge Base Completion Xixun Lin 1, Yanchun Liang 1,2, Fausto Giunchiglia 3, Xiaoyue Feng 1, Renchu Guan
More informationA Gradient-based Adaptive Learning Framework for Efficient Personal Recommendation
A Gradient-based Adaptive Learning Framework for Efficient Personal Recommendation Yue Ning 1 Yue Shi 2 Liangjie Hong 2 Huzefa Rangwala 3 Naren Ramakrishnan 1 1 Virginia Tech 2 Yahoo Research. Yue Shi
More informationTutorial on: Optimization I. (from a deep learning perspective) Jimmy Ba
Tutorial on: Optimization I (from a deep learning perspective) Jimmy Ba Outline Random search v.s. gradient descent Finding better search directions Design white-box optimization methods to improve computation
More informationCS281 Section 4: Factor Analysis and PCA
CS81 Section 4: Factor Analysis and PCA Scott Linderman At this point we have seen a variety of machine learning models, with a particular emphasis on models for supervised learning. In particular, we
More informationPROBABILISTIC KNOWLEDGE GRAPH CONSTRUCTION: COMPOSITIONAL AND INCREMENTAL APPROACHES. Dongwoo Kim with Lexing Xie and Cheng Soon Ong CIKM 2016
PROBABILISTIC KNOWLEDGE GRAPH CONSTRUCTION: COMPOSITIONAL AND INCREMENTAL APPROACHES Dongwoo Kim with Lexing Xie and Cheng Soon Ong CIKM 2016 1 WHAT IS KNOWLEDGE GRAPH (KG)? KG widely used in various tasks
More informationhttps://goo.gl/kfxweg KYOTO UNIVERSITY Statistical Machine Learning Theory Sparsity Hisashi Kashima kashima@i.kyoto-u.ac.jp DEPARTMENT OF INTELLIGENCE SCIENCE AND TECHNOLOGY 1 KYOTO UNIVERSITY Topics:
More informationLearning the Semantic Correlation: An Alternative Way to Gain from Unlabeled Text
Learning the Semantic Correlation: An Alternative Way to Gain from Unlabeled Text Yi Zhang Machine Learning Department Carnegie Mellon University yizhang1@cs.cmu.edu Jeff Schneider The Robotics Institute
More informationPROBABILISTIC KNOWLEDGE GRAPH EMBEDDINGS
PROBABILISTIC KNOWLEDGE GRAPH EMBEDDINGS Anonymous authors Paper under double-blind review ABSTRACT We develop a probabilistic extension of state-of-the-art embedding models for link prediction in relational
More informationJointly Embedding Knowledge Graphs and Logical Rules
Jointly Embedding Knowledge Graphs and Logical Rules Shu Guo, Quan Wang, Lihong Wang, Bin Wang, Li Guo Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093, China University
More informationThe Success of Deep Generative Models
The Success of Deep Generative Models Jakub Tomczak AMLAB, University of Amsterdam CERN, 2018 What is AI about? What is AI about? Decision making: What is AI about? Decision making: new data High probability
More informationRegularizing Knowledge Graph Embeddings via Equivalence and Inversion Axioms
Regularizing Knowledge Graph Embeddings via Equivalence and Inversion Axioms Pasquale Minervini 1, Luca Costabello 2, Emir Muñoz 1,2, Vít Nová ek 1 and Pierre-Yves Vandenbussche 2 1 Insight Centre for
More informationParallel and Distributed Stochastic Learning -Towards Scalable Learning for Big Data Intelligence
Parallel and Distributed Stochastic Learning -Towards Scalable Learning for Big Data Intelligence oé LAMDA Group H ŒÆOŽÅ Æ EâX ^ #EâI[ : liwujun@nju.edu.cn Dec 10, 2016 Wu-Jun Li (http://cs.nju.edu.cn/lwj)
More informationWilliam Yang Wang Department of Computer Science University of California, Santa Barbara Santa Barbara, CA USA
KBGAN: Adversarial Learning for Knowledge Graph Embeddings Liwei Cai Department of Electronic Engineering Tsinghua University Beijing 100084 China cai.lw123@gmail.com William Yang Wang Department of Computer
More informationKGBuilder: A System for Large-Scale Scientific Domain Knowledge Graph Building
XLDB2018 KGBuilder: A System for Large-Scale Scientific Domain Knowledge Graph Building Yi Zhang, Xiaofeng Meng WAMDM@RUC 5/3/2018 Knowledge Graph 什么是知识图谱 (Knowledge Graph)? Knowledge Graph Language Open
More informationArtificial Neural Networks D B M G. Data Base and Data Mining Group of Politecnico di Torino. Elena Baralis. Politecnico di Torino
Artificial Neural Networks Data Base and Data Mining Group of Politecnico di Torino Elena Baralis Politecnico di Torino Artificial Neural Networks Inspired to the structure of the human brain Neurons as
More informationLecture Notes 1: Vector spaces
Optimization-based data analysis Fall 2017 Lecture Notes 1: Vector spaces In this chapter we review certain basic concepts of linear algebra, highlighting their application to signal processing. 1 Vector
More informationGenerative Models for Sentences
Generative Models for Sentences Amjad Almahairi PhD student August 16 th 2014 Outline 1. Motivation Language modelling Full Sentence Embeddings 2. Approach Bayesian Networks Variational Autoencoders (VAE)
More informationExperiments on the Consciousness Prior
Yoshua Bengio and William Fedus UNIVERSITÉ DE MONTRÉAL, MILA Abstract Experiments are proposed to explore a novel prior for representation learning, which can be combined with other priors in order to
More informationarxiv: v4 [math.oc] 5 Jan 2016
Restarted SGD: Beating SGD without Smoothness and/or Strong Convexity arxiv:151.03107v4 [math.oc] 5 Jan 016 Tianbao Yang, Qihang Lin Department of Computer Science Department of Management Sciences The
More informationSparse vectors recap. ANLP Lecture 22 Lexical Semantics with Dense Vectors. Before density, another approach to normalisation.
ANLP Lecture 22 Lexical Semantics with Dense Vectors Henry S. Thompson Based on slides by Jurafsky & Martin, some via Dorota Glowacka 5 November 2018 Previous lectures: Sparse vectors recap How to represent
More informationANLP Lecture 22 Lexical Semantics with Dense Vectors
ANLP Lecture 22 Lexical Semantics with Dense Vectors Henry S. Thompson Based on slides by Jurafsky & Martin, some via Dorota Glowacka 5 November 2018 Henry S. Thompson ANLP Lecture 22 5 November 2018 Previous
More informationA Three-Way Model for Collective Learning on Multi-Relational Data
A Three-Way Model for Collective Learning on Multi-Relational Data 28th International Conference on Machine Learning Maximilian Nickel 1 Volker Tresp 2 Hans-Peter Kriegel 1 1 Ludwig-Maximilians Universität,
More informationReduced-Rank Hidden Markov Models
Reduced-Rank Hidden Markov Models Sajid M. Siddiqi Byron Boots Geoffrey J. Gordon Carnegie Mellon University ... x 1 x 2 x 3 x τ y 1 y 2 y 3 y τ Sequence of observations: Y =[y 1 y 2 y 3... y τ ] Assume
More informationCutting Plane Training of Structural SVM
Cutting Plane Training of Structural SVM Seth Neel University of Pennsylvania sethneel@wharton.upenn.edu September 28, 2017 Seth Neel (Penn) Short title September 28, 2017 1 / 33 Overview Structural SVMs
More informationDimensionality Reduction and Principle Components Analysis
Dimensionality Reduction and Principle Components Analysis 1 Outline What is dimensionality reduction? Principle Components Analysis (PCA) Example (Bishop, ch 12) PCA vs linear regression PCA as a mixture
More informationRecurrent Latent Variable Networks for Session-Based Recommendation
Recurrent Latent Variable Networks for Session-Based Recommendation Panayiotis Christodoulou Cyprus University of Technology paa.christodoulou@edu.cut.ac.cy 27/8/2017 Panayiotis Christodoulou (C.U.T.)
More informationEECS 275 Matrix Computation
EECS 275 Matrix Computation Ming-Hsuan Yang Electrical Engineering and Computer Science University of California at Merced Merced, CA 95344 http://faculty.ucmerced.edu/mhyang Lecture 22 1 / 21 Overview
More informationImplicit Optimization Bias
Implicit Optimization Bias as a key to Understanding Deep Learning Nati Srebro (TTIC) Based on joint work with Behnam Neyshabur (TTIC IAS), Ryota Tomioka (TTIC MSR), Srinadh Bhojanapalli, Suriya Gunasekar,
More informationNetwork Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec
Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec Jiezhong Qiu Tsinghua University February 21, 2018 Joint work with Yuxiao Dong (MSR), Hao Ma (MSR), Jian Li (IIIS,
More informationDifferentiable Learning of Logical Rules for Knowledge Base Reasoning
Differentiable Learning of Logical Rules for Knowledge Base Reasoning Fan Yang Zhilin Yang William W. Cohen School of Computer Science Carnegie Mellon University {fanyang1,zhiliny,wcohen}@cs.cmu.edu Abstract
More informationarxiv: v1 [cs.lg] 20 Jan 2019 Abstract
A tensorized logic programming language for large-scale data Ryosuke Kojima 1, Taisuke Sato 2 1 Department of Biomedical Data Intelligence, Graduate School of Medicine, Kyoto University, Kyoto, Japan.
More informationA Constraint Generation Approach to Learning Stable Linear Dynamical Systems
A Constraint Generation Approach to Learning Stable Linear Dynamical Systems Sajid M. Siddiqi Byron Boots Geoffrey J. Gordon Carnegie Mellon University NIPS 2007 poster W22 steam Application: Dynamic Textures
More informationReview: Linear and Vector Algebra
Review: Linear and Vector Algebra Points in Euclidean Space Location in space Tuple of n coordinates x, y, z, etc Cannot be added or multiplied together Vectors: Arrows in Space Vectors are point changes
More informationReview of Coordinate Systems
Vector in 2 R and 3 R Review of Coordinate Systems Used to describe the position of a point in space Common coordinate systems are: Cartesian Polar Cartesian Coordinate System Also called rectangular coordinate
More informationScalable Asynchronous Gradient Descent Optimization for Out-of-Core Models
Scalable Asynchronous Gradient Descent Optimization for Out-of-Core Models Chengjie Qin 1, Martin Torres 2, and Florin Rusu 2 1 GraphSQL, Inc. 2 University of California Merced August 31, 2017 Machine
More informationEve: A Gradient Based Optimization Method with Locally and Globally Adaptive Learning Rates
Eve: A Gradient Based Optimization Method with Locally and Globally Adaptive Learning Rates Hiroaki Hayashi 1,* Jayanth Koushik 1,* Graham Neubig 1 arxiv:1611.01505v3 [cs.lg] 11 Jun 2018 Abstract Adaptive
More informationICML Scalable Bayesian Inference on Point processes. with Gaussian Processes. Yves-Laurent Kom Samo & Stephen Roberts
ICML 2015 Scalable Nonparametric Bayesian Inference on Point Processes with Gaussian Processes Machine Learning Research Group and Oxford-Man Institute University of Oxford July 8, 2015 Point Processes
More informationFast Asynchronous Parallel Stochastic Gradient Descent: A Lock-Free Approach with Convergence Guarantee
Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence (AAAI-16) Fast Asynchronous Parallel Stochastic Gradient Descent: A Lock-Free Approach with Convergence Guarantee Shen-Yi Zhao and
More informationA Fast Augmented Lagrangian Algorithm for Learning Low-Rank Matrices
A Fast Augmented Lagrangian Algorithm for Learning Low-Rank Matrices Ryota Tomioka 1, Taiji Suzuki 1, Masashi Sugiyama 2, Hisashi Kashima 1 1 The University of Tokyo 2 Tokyo Institute of Technology 2010-06-22
More informationIntroduction to Machine Learning
10-701 Introduction to Machine Learning PCA Slides based on 18-661 Fall 2018 PCA Raw data can be Complex, High-dimensional To understand a phenomenon we measure various related quantities If we knew what
More informationECS289: Scalable Machine Learning
ECS289: Scalable Machine Learning Cho-Jui Hsieh UC Davis Oct 18, 2016 Outline One versus all/one versus one Ranking loss for multiclass/multilabel classification Scaling to millions of labels Multiclass
More informationECE521 W17 Tutorial 1. Renjie Liao & Min Bai
ECE521 W17 Tutorial 1 Renjie Liao & Min Bai Schedule Linear Algebra Review Matrices, vectors Basic operations Introduction to TensorFlow NumPy Computational Graphs Basic Examples Linear Algebra Review
More informationarxiv: v1 [cs.lg] 17 Sep 2017
On Inductive Abilities of Latent Factor Models for Relational Learning arxiv:1709.05666v1 [cs.lg] 17 Sep 2017 Théo Trouillon theo.trouillon@imag.fr Univ. Grenoble Alpes, 700 avenue Centrale, 38401 Saint
More informationCS145: INTRODUCTION TO DATA MINING
CS145: INTRODUCTION TO DATA MINING 5: Vector Data: Support Vector Machine Instructor: Yizhou Sun yzsun@cs.ucla.edu October 18, 2017 Homework 1 Announcements Due end of the day of this Thursday (11:59pm)
More informationRule Learning from Knowledge Graphs Guided by Embedding Models
Rule Learning from Knowledge Graphs Guided by Embedding Models Vinh Thinh Ho 1, Daria Stepanova 1, Mohamed Gad-Elrab 1, Evgeny Kharlamov 2, Gerhard Weikum 1 1 Max Planck Institute for Informatics, Saarbrücken,
More informationDeep Learning & Neural Networks Lecture 4
Deep Learning & Neural Networks Lecture 4 Kevin Duh Graduate School of Information Science Nara Institute of Science and Technology Jan 23, 2014 2/20 3/20 Advanced Topics in Optimization Today we ll briefly
More informationApproximating the Partition Function by Deleting and then Correcting for Model Edges (Extended Abstract)
Approximating the Partition Function by Deleting and then Correcting for Model Edges (Extended Abstract) Arthur Choi and Adnan Darwiche Computer Science Department University of California, Los Angeles
More informationECS289: Scalable Machine Learning
ECS289: Scalable Machine Learning Cho-Jui Hsieh UC Davis Oct 27, 2015 Outline One versus all/one versus one Ranking loss for multiclass/multilabel classification Scaling to millions of labels Multiclass
More informationRepresenting structured relational data in Euclidean vector spaces. Tony Plate
Representing structured relational data in Euclidean vector spaces Tony Plate tplate@acm.org http://www.d-reps.org October 2004 AAAI Symposium 2004 1 Overview A general method for representing structured
More informationRegularization Introduction to Machine Learning. Matt Gormley Lecture 10 Feb. 19, 2018
1-61 Introduction to Machine Learning Machine Learning Department School of Computer Science Carnegie Mellon University Regularization Matt Gormley Lecture 1 Feb. 19, 218 1 Reminders Homework 4: Logistic
More informationPURE MATHEMATICS AM 27
AM Syllabus (014): Pure Mathematics AM SYLLABUS (014) PURE MATHEMATICS AM 7 SYLLABUS 1 AM Syllabus (014): Pure Mathematics Pure Mathematics AM 7 Syllabus (Available in September) Paper I(3hrs)+Paper II(3hrs)
More informationCS168: The Modern Algorithmic Toolbox Lecture #10: Tensors, and Low-Rank Tensor Recovery
CS168: The Modern Algorithmic Toolbox Lecture #10: Tensors, and Low-Rank Tensor Recovery Tim Roughgarden & Gregory Valiant May 3, 2017 Last lecture discussed singular value decomposition (SVD), and we
More informationStein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm
Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm Qiang Liu and Dilin Wang NIPS 2016 Discussion by Yunchen Pu March 17, 2017 March 17, 2017 1 / 8 Introduction Let x R d
More informationUsing Joint Tensor Decomposition on RDF Graphs
Using Joint Tensor Decomposition on RDF Graphs Michael Hoffmann AKSW Group, Leipzig, Germany michoffmann.potsdam@gmail.com Abstract. The decomposition of tensors has on multiple occasions shown state of
More informationDeep Learning for NLP
Deep Learning for NLP CS224N Christopher Manning (Many slides borrowed from ACL 2012/NAACL 2013 Tutorials by me, Richard Socher and Yoshua Bengio) Machine Learning and NLP NER WordNet Usually machine learning
More information