23 citations · 96 across the 34 of their papers we have counts for
34 papers
Zipfian Whitening
Sho Yokoi, Han Bao, Hiroto Kurita +1
The word embedding space in neural models is skewed, and correcting this can improve task performance. We point out that most approaches for modeling, correcting, and measuring the…
Axis Tour: Word Tour Determines the Order of Axes in ICA-transformed Embeddings
Hiroaki Yamagiwa, Yusuke Takase, Hidetoshi Shimodaira
Word embedding is one of the most important components in natural language processing, but interpreting high-dimensional embeddings remains a challenging problem. To address this p…
Block-Diagonal Orthogonal Relation and Matrix Entity for Knowledge Graph Embedding
Yihua Zhu, Hidetoshi Shimodaira
The primary aim of Knowledge Graph embeddings (KGE) is to learn low-dimensional representations of entities and relations for predicting missing facts. While rotation-based methods…
Discovering Universal Geometry in Embeddings with ICA
Hiroaki Yamagiwa, Momose Oyama, Hidetoshi Shimodaira
This study utilizes Independent Component Analysis (ICA) to unveil a consistent semantic structure within embeddings of words or images. Our approach extracts independent semantic…
3D Rotation and Translation for Hyperbolic Knowledge Graph Embedding
Yihua Zhu, Hidetoshi Shimodaira
The main objective of Knowledge Graph (KG) embeddings is to learn low-dimensional representations of entities and relations, enabling the prediction of missing facts. A significant…
Norm of Word Embedding Encodes Information Gain
Momose Oyama, Sho Yokoi, Hidetoshi Shimodaira
Distributed representations of words encode lexical semantic information, but what type of information is encoded and how? Focusing on the skip-gram with negative-sampling method,…
Improving word mover's distance by leveraging self-attention matrix
Hiroaki Yamagiwa, Sho Yokoi, Hidetoshi Shimodaira
Measuring the semantic similarity between two sentences is still an important task. The word mover's distance (WMD) computes the similarity via the optimal alignment between the se…
Improving Nonparametric Classification via Local Radial Regression with an Application to Stock Prediction
Ruixing Cao, Akifumi Okuno, Kei Nakagawa +1
For supervised classification problems, this paper considers estimating the query's label probability through local regression using observed covariates. Well-known nonparametric k…
Revisiting Additive Compositionality: AND, OR and NOT Operations with Word Embeddings
Masahiro Naito, Sho Yokoi, Geewook Kim +1
It is well-known that typical word embedding methods such as Word2Vec and GloVe have the property that the meaning can be composed by adding up the embeddings (additive composition…
Nonparametric estimation of the preferential attachment function from one network snapshot
Thong Pham, Paul Sheridan, Hidetoshi Shimodaira
Preferential attachment is commonly invoked to explain the emergence of those heavy-tailed degree distributions characteristic of growing network representations of diverse real-wo…
Stochastic Neighbor Embedding of Multimodal Relational Data for Image-Text Simultaneous Visualization
Morihiro Mizutani, Akifumi Okuno, Geewook Kim +1
Multimodal relational data analysis has become of increasing importance in recent years, for exploring across different domains of data, such as images and their text tags obtained…
Extrapolation Towards Imaginary -Nearest Neighbour and Its Improved Convergence Rate
Akifumi Okuno, Hidetoshi Shimodaira
-nearest neighbour (-NN) is one of the simplest and most widely-used methods for supervised classification, that predicts a query's label by taking weighted ratio of observed…
More Powerful Selective Kernel Tests for Feature Selection
Jen Ning Lim, Makoto Yamada, Wittawat Jitkrittum +3
Refining one's hypotheses in the light of data is a common scientific practice; however, the dependency on the data introduces selection bias and can lead to specious statistical a…
Joint Estimation of the Non-parametric Transitivity and Preferential Attachment Functions in Scientific Co-authorship Networks
Masaaki Inoue, Thong Pham, Hidetoshi Shimodaira
We propose a statistical method to estimate simultaneously the non-parametric transitivity and preferential attachment functions in a growing network, in contrast to conventional m…
Hyperlink Regression via Bregman Divergence
Akifumi Okuno, Hidetoshi Shimodaira
A collection of data vectors is called a -tuple, and the association strength among the vectors of a tuple is termed as the \emph{hyperlink weight}, that…
Selective inference after feature selection via multiscale bootstrap
Yoshikazu Terada, Hidetoshi Shimodaira
It is common to show the confidence intervals or -values of selected features, or predictor variables in regression, but they often involve selection bias. The selective inferen…
An information criterion for auxiliary variable selection in incomplete data analysis
Shinpei Imori, Hidetoshi Shimodaira
Statistical inference is considered for variables of interest, called primary variables, when auxiliary variables are observed along with the primary variables. We consider the set…
Robust Graph Embedding with Noisy Link Weights
Akifumi Okuno, Hidetoshi Shimodaira
We propose -graph embedding for robustly learning feature vectors from data vectors and noisy link weights. A newly introduced empirical moment -score reduces the influence o…
Representation Learning with Weighted Inner Product for Universal Approximation of General Similarities
Geewook Kim, Akifumi Okuno, Kazuki Fukui +1
We propose (WIPS) for neural network-based graph embedding. In addition to the parameters of neural networks, we optimize the weights o…
Selective Inference for Testing Trees and Edges in Phylogenetics
Hidetoshi Shimodaira, Yoshikazu Terada
Selective inference is considered for testing trees and edges in phylogenetic tree selection from molecular sequences. This improves the previously proposed approximately unbiased…
Graph Embedding with Shifted Inner Product Similarity and Its Improved Approximation Capability
Akifumi Okuno, Geewook Kim, Hidetoshi Shimodaira
We propose shifted inner-product similarity (SIPS), which is a novel yet very simple extension of the ordinary inner-product similarity (IPS) for neural-network based graph embeddi…
Segmentation-free Compositional -gram Embedding
Geewook Kim, Kazuki Fukui, Hidetoshi Shimodaira
We propose a new type of representation learning method that models words, phrases and sentences seamlessly. Our method does not depend on word segmentation and any human-annotated…
On representation power of neural network-based graph embedding and beyond
Akifumi Okuno, Hidetoshi Shimodaira
We consider the representation power of siamese-style similarity functions used in neural network-based graph embedding. The inner product similarity (IPS) with feature vectors com…
A probabilistic framework for multi-view feature learning with many-to-many associations via neural networks
Akifumi Okuno, Tetsuya Hada, Hidetoshi Shimodaira
A simple framework Probabilistic Multi-view Graph Embedding (PMvGE) is proposed for multi-view feature learning with many-to-many associations so that it generalizes various existi…