Our paper on predicting commuter demands on urban railways is accepted to the Web Conference (WWW) as a short paper：

Yohei Kodama, Yuki Akeyama, Yusuke Miyazaki, Koh Takeuchi.
Travel Demand Prediction with Application to Commuter Demand Estimation on Urban Railways.
In Proceedings of the 2024 ACM Web Conference), 2024.

Our paper on comparing human and machine evaluation of XAI methods in NLP tasks was accepted for LREC-COLING 2024, an international conference on natural language processing:

Xiaotian Lu, Jiyi Li, Zhen Wan, Xiaofeng Lin, Koh Takeuchi, Hisashi Kashima.
Evaluating Saliency Explanations in NLP by Crowdsourcing.
In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING), 2024.

A paper proposing a regularization method for neural networks that generates synthetic samples according to the training status of a classifier by meta-optimizing the generative model and uses them to train a feature extractor has been accepted to the Asian Conference on Machine Learning (ACML 2023):

Shin'ya Yamaguchi.
Generative Semi-supervised Learning with Meta-Optimized Synthetic Samples.
In Proceedings of the 15th Asian Conference on Machine Learning (ACML), 2023.

Our paper proposing a method for estimating individual treatment effects on graphs representing multiple types of relationships has been accepted to ECML PKDD 2023, an international conference in the field of machine learning and data mining:

Xiaofeng Lin, Guoxi Zhang, Xiaotian Lu, Han Bao, Koh Takeuchi, Hisashi Kashima.
Estimating Treatment Effects Under Heterogeneous Interference.
In Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), 2023.

Two papers from our lab were accepted for The 29th SIGKDD Conference on Knowledge Discovery and Data Mining (KDD):

Koh Takeuchi, Ryo Nishida, Hisashi Kashima, Masaki Onishi.
Causal Effect Estimation on Hierarchical Spatial Graph Data.
In Proceedings of the 29th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2023.
- Proposed Spatial Intervention Neural Network (SINet) to estimate causal effects on spatial graph data.

Ryu Shirakami, Toshiya Kitahara, Koh Takeuchi, Hisashi Kashima. QTNet: Theory-based Queue Length Prediction for Urban Traffic.  In Proceedings of the 29th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2023. 
- Proposed Queueing-theory-based Neural Network (QT-Net) to predict traffic queue lengths in urban transportation networks.

A paper showing that the convergence rate of proper loss, which is commonly used in classification is governed by the modulus of convexity of the generalized entropy function has been accepted by the Conference on Learning Theory (COLT).

Han Bao.
Proper Losses, Moduli of Convexity, and Surrogate Regret Bounds.
In Proceedings of the 36th Conference on Learning Theory (COLT), 2023.

A paper evaluating the behavior of imbalanced optimal transport in word alignment with a large number of uncorresponding word pairs has been accepted for publication in the Annual Meeting of the Association for Computational Linguistics (ACL).

Yuki Arase, Han Bao, Sho Yokoi.
Unbalanced Optimal Transport for Unbalanced Word Alignment.
In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL), 2023.

Our paper proposing a method for unbiased opinion aggregation in attribute-biased populations has been accepted to the AAAI/ACM Conference on AI, Ethics, and Society (AIES 2023), an international conference on the ethics and social impact of AI:

Ryosuke Ueda, Koh Takeuchi, Hisashi Kashima.
Fair Opinion Aggregation for Voter Attribute Bias.
In Proceedings of 6th AAAI/ACM Conference on AI, Ethics, and Society (AIES), 2023.

Research proving that graph neural networks can create new useful node features that are not included in the input node features has been accepted to ICML2023:

Ryoma Sato. Graph Neural Networks can Recover the Hidden Features Solely from the Graph Structure. In Proceedings of the 40th International Conference on Machine Learning (ICML), 2023. 

Two papers from our lab were accepted for The 29th SIGKDD Conference on Knowledge Discovery and Data Mining (KDD).

Koh Takeuchi, Ryo Nishida, Hisashi Kashima, Masaki Onishi.
Causal Effect Estimation on Hierarchical Spatial Graph Data.
In Proceedings of the 29th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2023.
# Proposed the Spatial Intervention Graph Neural Networks (SINet) to predict causal effect on spatial graph data.

Ryu Shirakami, Toshiya Kitahara, Koh Takeuchi, Hisashi Kashima.
QTNet: Theory-based Queue Length Prediction for Urban Traffic. 
In Proceedings of the 29th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2023.
# Proposed the Queueing-theory-based Neural Network (QT-Net) to predict traffic queue lengths.

Our paper proposing a method for off-line deep reinforcement learning methods from mixed-behavior episode data obtained from several different policies was accepted to AAAI 2023, a top conference in the field of AI.

Guoxi Zhang, Hisashi Kashima.
Behavior Estimation from Multi-Source Data for Offline Reinforcement Learning.
In Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI), 2022.

Our paper proposing a variational inference method for factorization machines and applying it to recommendation systems was accepted to IEEE BigData 2022.

Jill-Jênn Vie, Tomas Rigaux, Hisashi Kashima.
Variational Factorization Machines for Preference Elicitation in Large-Scale Recommender Systems.
In Proceedings of the 2022 IEEE International Conference on Big Data (BigData), 2022.

Our paper, “Anisotropic Estimation of Station Market Areas by Supervised Learning Using Geospatial Information and IC Commuter Pass Data“, is selected as JSAI Annual Conference Award at The 36th Annual Conference of the Japanese Society for Artificial Intelligence, 2022.
Yohei Kodama, Yuki Akeyama, Yusuke Miyazaki, and Koh Takeuchi.
“Anisotropic Estimation of Station Market Areas by Supervised Learning Using Geospatial Information and IC Commuter Pass Data“
Proceedings of JSAI 2022
List of JSAI Annual Conference Award

Our paper, “Estimating counterfactual treatment outcomes over time in multi-vehicle simulation”, was selected as the best poster award at 30th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (ACM SIGSPATIAL 2022).

Keisuke Fujii (Nagoya University), Koh Takeuchi (Kyoto University), Atsushi Kuribayashi (Nagoya University), Naoya Takeishi (HES-SO), Yoshinobu Kawahara (Kyushu University), and Kazuya Takeda (Nagoya University).
Estimating counterfactual treatment outcomes over time in multi-vehicle simulation
(Paper, Video)

30th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (ACM SIGSPATIAL 2022) 
Tuesday November 1 – Friday November 4, 2022 Seattle, Washington, USA

A paper proposing a method for estimating intervention effects while estimating confounding variables when they are not observed, and a paper proposing a method for estimating state importance in reinforcement learning from pairwise comparisons of episodes have been accepted for publication in the Machine Learning Journal (ACML Journal Track).

Shonosuke Harada, Hisashi Kashima.
InfoCEVAE: Treatment Effect Estimation with Hidden Confounding Variables Matching.
Machine Learning, 2022.

Guoxi Zhang, Hisashi Kashima.
Learning State Importance for Preference-based Reinforcement Learning.
Machine Learning, 2022.

Our paper proposing a novel ranking method using queries comparing rank differences of two pairs of items was accepted for the 9th IEEE International Conference on Data Science and Advanced Analytics (DSAA).

Guoxi Zhang, Jiyi Li, Hisashi Kashima.
Improving Pairwise Rank Aggregation via Querying for Rank Difference.
In Proceedings of the 9th IEEE International Conference on Data Science and Advanced Analytics (DSAA), 2022.

Three papers were accepted for Conference on Information and Knowledge Management (CIKM):

Ryoma Sato.
Towards Principled User-side Recommender Systems.
In Proceedings of the 31st ACM International Conference on Information and Knowledge Management (CIKM), 2022.
# Demonstrated the theoretical feasibility of a user-side recommendation system and proposed a user-side recommendation algorithm with desirable properties

Ryoma Sato.
CLEAR: A Fully User-side Image Search System.
In Proceedings of the 31st ACM International Conference on Information and Knowledge Management (CIKM), 2022.
# A demonstration working in a browser that performs image searches based on a score function set by a user.

Ryoma Sato, Makoto Yamada, Hisashi Kashima.
Twin Papers: A Simple Framework of Causal Inference for Citations via Coupling.
In Proceedings of the 31st ACM International Conference on Information and Knowledge Management (CIKM), 2022.
# Proposed a method for analyzing research impact using causal inference based on "twin papers".

Our paper proposing learning a fair predictor based on the notion of “causal pathways” was accepted for Data Mining and Knowledge Discovery (DAMI) journal:

Yoichi Chikahara, Shinsaku Sakaue, Akinori Fujino, Hisashi Kashima.
Making Individually Fair Predictions with Causal Pathways.
Data Mining and Knowledge Discovery (DAMI), 2022.

Two papers were accepted for ECML PKDD, a premier conference on machine learning and data mining:

Guoxi Zhang, Hisashi Kashima.
Batch Reinforcement Learning from Crowds.
In Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), 2022.

Mathis Petrovich, Chao Liang, Ryoma Sato, Yanbin Liu, Yao-Hung Hubert Tsai, Linchao Zhu, Yi Yang, Ruslan Salakhutdinov, Makoto Yamada.
Feature Robust Optimal Transport for High-dimensional Data.
In Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), 2022.

Our paper proposing a new conditional VAE (CVAE) that acquires task-invariant latent variables across different tasks has been accepted to KDD2022.

Hiroshi Takahashi, Tomoharu Iwata, Atsutoshi Kumagai, Sekitoshi Kanai, Masanori Yamada, Yuuki Yamanaka, Hisashi Kashima.
Learning Optimal Priors for Task-Invariant Representations in Variational Autoencoders.
In Proceedings of the 28th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2022.