Search Results for author: Ken-ichi Kawarabayashi

Found 26 papers, 7 papers with code

RelWalk - A Latent Variable Model Approach to Knowledge Graph Embedding

no code implementations EACL 2021 Danushka Bollegala, Huda Hakami, Yuichi Yoshida, Ken-ichi Kawarabayashi

Embedding entities and relations of a knowledge graph in a low-dimensional space has shown impressive performance in predicting missing links between entities.

Knowledge Graph Embedding Knowledge Graph Embeddings +1

RelWalk A Latent Variable Model Approach to Knowledge Graph Embedding

1 code implementation25 Jan 2021 Danushka Bollegala, Huda Hakami, Yuichi Yoshida, Ken-ichi Kawarabayashi

Embedding entities and relations of a knowledge graph in a low-dimensional space has shown impressive performance in predicting missing links between entities.

Knowledge Graph Embedding Knowledge Graph Embeddings +1

Near-Optimal Regret Bounds for Contextual Combinatorial Semi-Bandits with Linear Payoff Functions

no code implementations20 Jan 2021 Kei Takemura, Shinji Ito, Daisuke Hatano, Hanna Sumita, Takuro Fukunaga, Naonori Kakimura, Ken-ichi Kawarabayashi

However, there is a gap of $\tilde{O}(\max(\sqrt{d}, \sqrt{k}))$ between the current best upper and lower bounds, where $d$ is the dimension of the feature vectors, $k$ is the number of the chosen arms in a round, and $\tilde{O}(\cdot)$ ignores the logarithmic factors.

Decision Making Recommendation Systems

How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks

3 code implementations ICLR 2021 Keyulu Xu, Mozhi Zhang, Jingling Li, Simon S. Du, Ken-ichi Kawarabayashi, Stefanie Jegelka

Second, in connection to analyzing the successes and limitations of GNNs, these results suggest a hypothesis for which we provide theoretical and empirical evidence: the success of GNNs in extrapolating algorithmic tasks to new data (e. g., larger graphs or edge weights) relies on encoding task-specific non-linearities in the architecture or features.

Automorphism groups of maps in linear time

no code implementations4 Aug 2020 Ken-ichi Kawarabayashi, Bojan Mohar, Roman Nedela, Peter Zeman

The automorphism group of the original map can be reconstructed from the automorphism group of the uniform map in linear time.

Combinatorics Data Structures and Algorithms

Oracle-Efficient Algorithms for Online Linear Optimization with Bandit Feedback

no code implementations NeurIPS 2019 Shinji Ito, Daisuke Hatano, Hanna Sumita, Kei Takemura, Takuro Fukunaga, Naonori Kakimura, Ken-ichi Kawarabayashi

Our algorithm for non-stochastic settings has an oracle complexity of $\tilde{O}( T )$ and is the first algorithm that achieves both a regret bound of $\tilde{O}( \sqrt{T} )$ and an oracle complexity of $\tilde{O} ( \mathrm{poly} ( T ) )$, given only linear optimization oracles.

Improved Regret Bounds for Bandit Combinatorial Optimization

no code implementations NeurIPS 2019 Shinji Ito, Daisuke Hatano, Hanna Sumita, Kei Takemura, Takuro Fukunaga, Naonori Kakimura, Ken-ichi Kawarabayashi

\textit{Bandit combinatorial optimization} is a bandit framework in which a player chooses an action within a given finite set $\mathcal{A} \subseteq \{ 0, 1 \}^d$ and incurs a loss that is the inner product of the chosen action and an unobservable loss vector in $\mathbb{R} ^ d$ in each round.

Combinatorial Optimization

Anonymising Queries by Semantic Decomposition

no code implementations12 Sep 2019 Danushka Bollegala, Tomoya Machide, Ken-ichi Kawarabayashi

Next, we reconstruct the search results relevant to the original query term by aggregating the search results retrieved for the decomposed query terms.

Information Retrieval Word Embeddings

Are Girls Neko or Sh\=ojo? Cross-Lingual Alignment of Non-Isomorphic Embeddings with Iterative Normalization

no code implementations ACL 2019 Mozhi Zhang, Keyulu Xu, Ken-ichi Kawarabayashi, Stefanie Jegelka, Jordan Boyd-Graber

Cross-lingual word embeddings (CLWE) underlie many multilingual natural language processing systems, often through orthogonal transformations of pre-trained monolingual embeddings.

Translation Word Embeddings

Are Girls Neko or Shōjo? Cross-Lingual Alignment of Non-Isomorphic Embeddings with Iterative Normalization

1 code implementation4 Jun 2019 Mozhi Zhang, Keyulu Xu, Ken-ichi Kawarabayashi, Stefanie Jegelka, Jordan Boyd-Graber

Cross-lingual word embeddings (CLWE) underlie many multilingual natural language processing systems, often through orthogonal transformations of pre-trained monolingual embeddings.

Translation Word Embeddings

RelWalk -- A Latent Variable Model Approach to Knowledge Graph Embedding

no code implementations ICLR 2019 Danushka Bollegala, Huda Hakami, Yuichi Yoshida, Ken-ichi Kawarabayashi

Existing methods for learning KGEs can be seen as a two-stage process where (a) entities and relations in the knowledge graph are represented using some linear algebraic structures (embeddings), and (b) a scoring function is defined that evaluates the strength of a relation that holds between two entities using the corresponding relation and entity embeddings.

Entity Embeddings Knowledge Graph Embedding +1

Regret Bounds for Online Portfolio Selection with a Cardinality Constraint

no code implementations NeurIPS 2018 Shinji Ito, Daisuke Hatano, Sumita Hanna, Akihiro Yabe, Takuro Fukunaga, Naonori Kakimura, Ken-ichi Kawarabayashi

Online portfolio selection is a sequential decision-making problem in which a learner repetitively selects a portfolio over a set of assets, aiming to maximize long-term return.

Decision Making

Representation Learning on Graphs with Jumping Knowledge Networks

2 code implementations ICML 2018 Keyulu Xu, Chengtao Li, Yonglong Tian, Tomohiro Sonobe, Ken-ichi Kawarabayashi, Stefanie Jegelka

Furthermore, combining the JK framework with models like Graph Convolutional Networks, GraphSAGE and Graph Attention Networks consistently improves those models' performance.

Graph Attention Node Classification +1

Causal Bandits with Propagating Inference

no code implementations ICML 2018 Akihiro Yabe, Daisuke Hatano, Hanna Sumita, Shinji Ito, Naonori Kakimura, Takuro Fukunaga, Ken-ichi Kawarabayashi

In this setting, the arms are identified with interventions on a given causal graph, and the effect of an intervention propagates throughout all over the causal graph.

ClassiNet -- Predicting Missing Features for Short-Text Classification

no code implementations14 Apr 2018 Danushka Bollegala, Vincent Atanasov, Takanori Maehara, Ken-ichi Kawarabayashi

We propose \emph{ClassiNet} -- a network of classifiers trained for predicting missing features in a given instance, to overcome the feature sparseness problem.

General Classification Text Classification

Joint Word Representation Learning using a Corpus and a Semantic Lexicon

1 code implementation19 Nov 2015 Danushka Bollegala, Alsuhaibani Mohammed, Takanori Maehara, Ken-ichi Kawarabayashi

For this purpose, we propose a joint word representation learning method that simultaneously predicts the co-occurrences of two words in a sentence subject to the relational constrains given by the semantic lexicon.

Representation Learning Semantic Similarity +1

Unsupervised Cross-Domain Word Representation Learning

no code implementations IJCNLP 2015 Danushka Bollegala, Takanori Maehara, Ken-ichi Kawarabayashi

Given a pair of \emph{source}-\emph{target} domains, we propose an unsupervised method for learning domain-specific word representations that accurately capture the domain-specific aspects of word semantics.

Domain Adaptation Representation Learning +1

Embedding Semantic Relations into Word Representations

no code implementations1 May 2015 Danushka Bollegala, Takanori Maehara, Ken-ichi Kawarabayashi

We propose an unsupervised method for learning vector representations for words such that the learnt representations are sensitive to the semantic relations that exist between two words.

Relation Classification

Learning Word Representations from Relational Graphs

no code implementations7 Dec 2014 Danushka Bollegala, Takanori Maehara, Yuichi Yoshida, Ken-ichi Kawarabayashi

To evaluate the accuracy of the word representations learnt using the proposed method, we use the learnt word representations to solve semantic word analogy problems.

Representation Learning

Generating Approximate Solutions to the TTP using a Linear Distance Relaxation

no code implementations23 Jan 2014 Richard Hoshino, Ken-ichi Kawarabayashi

For larger n, we propose a novel "expander construction" that generates an approximate solution to the LD-TTP.

Cannot find the paper you are looking for? You can Submit a new open access paper.