155 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- National Institute of Advanced Industrial Science and TechnologyJP35 papers
- The University of TokyoJP9 papers
- Tokyo Institute of TechnologyJP8 papers
- Waseda UniversityJP5 papers
- Ochanomizu UniversityJP4 papers
- Institute of Space and Astronautical ScienceJP3 papers
- Japan Aerospace Exploration AgencyJP3 papers
- Nara Institute of Science and TechnologyJP3 papers
- The University of OsakaJP3 papers
- Fujitsu (Japan)JP2 papers
- Hokkaido Information UniversityJP2 papers
- Hokkaido UniversityJP2 papers
40 papers
Speeding Up Multi-Objective Hyperparameter Optimization by Task Similarity-Based Meta-Learning for the Tree-Structured Parzen Estimator
Shuhei Watanabe, Noor Awad, Masaki Onishi +1
Hyperparameter optimization (HPO) is a vital step in improving performance in deep learning (DL). Practitioners are often faced with the trade-off between multiple criteria, such a…
Finding community structure using the ordered random graph model
Masaki Ochi, Tatsuro Kawamoto
Visualization of the adjacency matrix enables us to capture macroscopic features of a network when the matrix elements are aligned properly. Community structure, a network consisti…
Consistency between ordering and clustering methods for graphs
Tatsuro Kawamoto, Masaki Ochi, Teruyoshi Kobayashi
A relational dataset is often analyzed by optimally assigning a label to each element through clustering or ordering. While similar characterizations of a dataset would be achieved…
Single-trajectory map equation
Tatsuro Kawamoto
Community detection, the process of identifying module structures in complex systems represented on networks, is an effective tool in various fields of science. The map equation, w…
Contribution of directedness in graph spectra
Masaki Ochi, Tatsuro Kawamoto
In graph analyses, directed edges are often approximated to undirected ones so that the adjacency matrices may be symmetric. However, such simplification has not been thoroughly ve…
Sequential locality of graphs and its hypothesis testing
Tatsuro Kawamoto, Teruyoshi Kobayashi
The adjacency matrix is the most fundamental and intuitive object in graph analysis that is useful not only mathematically but also for visualizing the structures of graphs. Becaus…
A Topological Solution of Entanglement for Complex-shaped Parts in Robotic Bin-picking
Xinyi Zhang, Keisuke Koyama, Yukiyasu Domae +2
This paper addresses the problem of picking up only one object at a time avoiding any entanglement in bin-picking. To cope with a difficult case where the complex-shaped objects ar…
Balanced softmax cross-entropy for incremental learning with and without memory
Quentin Jodelet, Xin Liu, Tsuyoshi Murata
When incrementally trained on new classes, deep neural networks are subject to catastrophic forgetting which leads to an extreme deterioration of their performance on the old class…
Stable deep reinforcement learning method by predicting uncertainty in rewards as a subtask
Kanata Suzuki, Tetsuya Ogata
In recent years, a variety of tasks have been accomplished by deep reinforcement learning (DRL). However, when applying DRL to tasks in a real-world environment, designing an appro…
Graph-based open-ended survey on concerns related to COVID-19
Tatsuro Kawamoto, Takaaki Aoki, Michiko Ueda
The COVID-19 pandemic is an unprecedented public health crisis with broad social and economic consequences. We conducted four surveys between April and August 2020 using the graph-…
Understanding Approximate Fisher Information for Fast Convergence of Natural Gradient Descent in Wide Neural Networks
Ryo Karakida, Kazuki Osawa
Natural Gradient Descent (NGD) helps to accelerate the convergence of gradient descent dynamics, but it requires approximations in large-scale deep neural networks because of its h…
Graph Convolutional Networks for Graphs Containing Missing Features
Hibiki Taguchi, Xin Liu, Tsuyoshi Murata
Graph Convolutional Network (GCN) has experienced great success in graph analysis tasks. It works by smoothing the node features across the graph. The current GCN models overwhelmi…
GeoFlink: A Distributed and Scalable Framework for the Real-time Processing of Spatial Streams
Salman Ahmed Shaikh, Komal Mariam, Hiroyuki Kitagawa +1
Apache Flink is an open-source system for scalable processing of batch and streaming data. Flink does not natively support efficient processing of spatial data streams, which is a…
Planning an Efficient and Robust Base Sequence for a Mobile Manipulator Performing Multiple Pick-and-place Tasks
Jingren Xu, Kensuke Harada, Weiwei Wan +2
In this paper, we address efficiently and robustly collecting objects stored in different trays using a mobile manipulator. A resolution complete method, based on precomputed reach…
A Sparse Representation Based Joint Demosaicing Method for Single-Chip Polarized Color Sensor
Sijia Wen, Yinqiang Zheng, Feng Lu
The emergence of the single-chip polarized color sensor now allows for simultaneously capturing chromatic and polarimetric information of the scene on a monochromatic image plane.…
Pathological spectra of the Fisher information metric and its variants in deep neural networks
Ryo Karakida, Shotaro Akaho, Shun-ichi Amari
The Fisher information matrix (FIM) plays an essential role in statistics and machine learning as a Riemannian metric tensor or a component of the Hessian matrix of loss functions.…
Planetary-scale variations in winds and UV brightness at the Venusian cloud top: Periodicity and temporal evolution
Masataka Imai, Toru Kouyama, Yukihiro Takahashi +9
Planetary-scale waves at the Venusian cloud-top cause periodic variations in both winds and ultraviolet (UV) brightness. While the wave candidates are the 4-day Kelvin wave and 5-d…
Transfer Fine-Tuning: A BERT Case Study
Yuki Arase, Junichi Tsujii
A semantic equivalence assessment is defined as a task that assesses semantic equivalence in a sentence pair by binary judgment (i.e., paraphrase identification) or grading (i.e.,…
Learning to Select, Track, and Generate for Data-to-Text
Hayate Iso, Yui Uehara, Tatsuya Ishigaki +6
We propose a data-to-text generation model with two modules, one for tracking and the other for text generation. Our tracking module selects and keeps track of salient information…
Democratic summary of public opinions in free-response surveys
Tatsuro Kawamoto, Takaaki Aoki
Social surveys have been widely used as a method of obtaining public opinion. Sometimes it is more ideal to collect opinions by presenting questions in free-response formats than i…
Semi-supervised Approach to Soft Sensor Modeling for Fault Detection in Industrial Systems with Multiple Operation Modes
Shun Takeuchi, Takuya Nishino, Takahiro Saito +1
In industrial systems, certain process variables that need to be monitored for detecting faults are often difficult or impossible to measure. Soft sensor techniques are widely used…
CARAVAN: a framework for comprehensive simulations on massive parallel machines
Yohsuke Murase, Hiroyasu Matsushima, Itsuki Noda +1
We present a software framework called CARAVAN, which was developed for comprehensive simulations on massive parallel computers. The framework runs user-developed simulators with v…
Combining Axiom Injection and Knowledge Base Completion for Efficient Natural Language Inference
Masashi Yoshikawa, Koji Mineshima, Hiroshi Noji +1
In logic-based approaches to reasoning tasks such as Recognizing Textual Entailment (RTE), it is important for a system to have a large amount of knowledge data. However, there is…
Mean-field theory of graph neural networks in graph partitioning
Tatsuro Kawamoto, Masashi Tsubaki, Tomoyuki Obuchi
A theoretical performance analysis of the graph neural network (GNN) is presented. For classification tasks, the neural network approach has the advantage in terms of flexibility t…