過去のお知らせ
-
協調フィルタリングにおけるBias Disparityの削減に取り組んだ研究がComputing Systems分野におけるトップジャーナルIEEE Transactions on Services Computing（IF=5.5）に採択されました！
Hiroki Okamura, Keisuke Maeda, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Linear structure analysis of embeddings for bias disparity reduction in collaborative filtering” (Accepted for publication)
https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=4629386
-
脳活動情報を導入した敵対的防御の強化に関する論文が学術論文誌Sensors（IF=3.4）に採択されました！
Tasuku Nakajima, Keisuke Maeda, Ren Togo, Takahiro Ogawa, and Miki Haseyama, “Enhancing adversarial defense via brain activity integration without adversarial examples,” Sensors, 2025.
-
世界最高峰の信号処理に関する国際会議 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2025)にて発表を行いました！
インド ハイデラバードで開催されたICASSP2025にて、以下の論文を発表しました。
https://2025.ieeeicassp.org【Regular Track】
[1] Ren Tasai, Guang Li, Ren Togo, Minghui Tang, Takaaki Yoshimura, Hiroyuki Sugimori, Kenji Hirata, Takahiro Ogawa, Kohsuke Kudo, Miki Haseyama, “Continuous Self-Supervised Learning Considering Medical Domain Knowledge in Chest CT Images”
[2] Longzhen Li, Guang Li, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “Generative Dataset Distillation Based on Self-knowledge Distillation”
[3] Kenta Kubota, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “Gradient-oriented Clustered Federated Learning with Efficient Knowledge Sharing in Non-IID Settings”
[4] Kenta Uesugi, Naoki Saito, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation”
[5] Koshiro Toishi, Keisuke Maeda, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Robust Adversarial Defense Based on Non-Transferability of Attack across Foundation Models”【OJSP Track】
[6] Taro Togo, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “Enhancing Generative Class Incremental Learning Performance with a Model Forgetting Approach”
[7] Xiang Li, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “Enhancing Classification Models with Sophisticated Counterfactual Images”
-
情報検索分野のトップカンファレンスECIR2025(採択率23%)にて発表を行いました！
2025年4月6日-10日にイタリア・ルッカで開催された情報検索分野のトップカンファレンス European Conference on Information Retrieval (ECIR2025) にて、当研究室からLLMと知識グラフに基づく推薦技術に関する研究成果を発表しました (採択率23%)。
Keigo Sakurai, Ren Togo, Takahiro Ogawa, Miki Haseyama, “LLM is Knowledge Graph Reasoner: LLM’s Intuition-aware Knowledge Graph Reasoning for Cold-start Sequential Recommendation,” in Proceedings of the European Conference on Information Retrieval, pp.263-278, 2025.
