45 citations · 103 across the 13 of their papers we have counts for
14 papers
CASTANET: Causality-Aware Spatio-Temporal Adversarial Network Using Traffic Incident Effects
Toshiya Kitahara, Ryu Shirakami, Koh Takeuchi +1
Predicting non-periodic traffic congestion caused by sudden incidents (e.g., accidents and road damage) is crucial for advanced intelligent transportation systems. However, inciden…
Mitigating Voter Attribute Bias for Fair Opinion Aggregation
Ryosuke Ueda, Koh Takeuchi, Hisashi Kashima
The aggregation of multiple opinions plays a crucial role in decision-making, such as in hiring and loan review, and in labeling data for supervised learning. Although majority vot…
Mitigating Observation Biases in Crowdsourced Label Aggregation
Ryosuke Ueda, Koh Takeuchi, Hisashi Kashima
Crowdsourcing has been widely used to efficiently obtain labeled datasets for supervised learning from large numbers of human resources at low cost. However, one of the technical c…
Multiview Representation Learning from Crowdsourced Triplet Comparisons
Xiaotian Lu, Jiyi Li, Koh Takeuchi +1
Crowdsourcing has been used to collect data at scale in numerous fields. Triplet similarity comparison is a type of crowdsourcing task, in which crowd workers are asked the questio…
Estimating counterfactual treatment outcomes over time in complex multiagent scenarios
Keisuke Fujii, Koh Takeuchi, Atsushi Kuribayashi +3
Evaluation of intervention in a multiagent system, e.g., when humans should intervene in autonomous driving systems and when a player should pass to teammates for a good shot, is c…
Interpretable Knowledge Tracing: Simple and Efficient Student Modeling with Causal Relations
Sein Minn, Jill-Jenn Vie, Koh Takeuchi +2
Intelligent Tutoring Systems have become critically important in future learning environments. Knowledge Tracing (KT) is a crucial part of that system. It is about inferring the sk…
Crowdsourcing Evaluation of Saliency-based XAI Methods
Xiaotian Lu, Arseny Tolmachev, Tatsuya Yamamoto +5
Understanding the reasons behind the predictions made by deep neural networks is critical for gaining human trust in many important applications, which is reflected in the increasi…
Inter-domain Multi-relational Link Prediction
Luu Huu Phuc, Koh Takeuchi, Seiji Okajima +4
Multi-relational graph is a ubiquitous and important data structure, allowing flexible representation of multiple types of interactions and relations between entities. Similar to o…
Discriminant Dynamic Mode Decomposition for Labeled Spatio-Temporal Data Collections
Naoya Takeishi, Keisuke Fujii, Koh Takeuchi +1
Extracting coherent patterns is one of the standard approaches towards understanding spatio-temporal data. Dynamic mode decomposition (DMD) is a powerful tool for extracting cohere…
Grab the Reins of Crowds: Estimating the Effects of Crowd Movement Guidance Using Causal Inference
Koh Takeuchi, Ryo Nishida, Hisashi Kashima +1
Crowd movement guidance has been a fascinating problem in various fields, such as easing traffic congestion in unusual events and evacuating people from an emergency-affected area.…
Succinct Trit-array Trie for Scalable Trajectory Similarity Search
Shunsuke Kanda, Koh Takeuchi, Keisuke Fujii +1
Massive datasets of spatial trajectories representing the mobility of a diversity of moving objects are ubiquitous in research and industry. Similarity search of a large collection…
Non-linear Attributed Graph Clustering by Symmetric NMF with PU Learning
Seiji Maekawa, Koh Takeuch, Makoto Onizuka
We consider the clustering problem of attributed graphs. Our challenge is how we can design an effective and efficient clustering method that precisely captures the hidden relation…
Few-shot learning of neural networks from scratch by pseudo example optimization
Akisato Kimura, Zoubin Ghahramani, Koh Takeuchi +2
In this paper, we propose a simple but effective method for training neural networks with a limited amount of training data. Our approach inherits the idea of knowledge distillatio…
Localized Lasso for High-Dimensional Regression
Makoto Yamada, Koh Takeuchi, Tomoharu Iwata +2
We introduce the localized Lasso, which is suited for learning models that are both interpretable and have a high predictive power in problems with high dimensionality and smal…