Portfolio item number 2
Short description of portfolio item number 2 
Short description of portfolio item number 2 
Published in IEEE Global Conference on Consumer Electronics (GCCE), 2025
Recommended citation: Keito Kozaki, Keigo Sakurai, Ren Togo, Takahiro Ogawa, Miki Haseyama. (2025). "SSM-Based Sequential Recommendation Considering Short-Term Dependencies of Time and Adjacency." Proceedings of the IEEE Global Conference on Consumer Electronics (GCCE), pp. 1271-1274.
Published in 令和7年度 電気・情報関係学会北海道支部連合大会, 2025
Recommended citation: 神崎恵土, 櫻井慶悟, 藤後廉, 小川貴弘, 長谷山美紀. (2025). "ユーザ行動系列エンコーダの周波数特性を考慮した逐次推薦モデルに関する検討." 令和7年度 電気・情報関係学会北海道支部連合大会 講演論文集, pp. 37-38.
Published in 第18回データ工学と情報マネジメントに関するフォーラム (DEIM2026), 2026
Recommended citation: 神崎恵土, 櫻井慶悟, 藤後廉, 小川貴弘, 長谷山美紀. (2026). "因果的Self-Attentionを用いた逐次推薦モデルにおける残差支配がもたらす最終アイテム依存." 第18回データ工学と情報マネジメントに関するフォーラム (DEIM2026).
Published in 2026年度 人工知能学会全国大会 (JSAI), 2026
Recommended citation: 神崎恵土, 櫻井慶悟, 藤後廉, 小川貴弘, 長谷山美紀. (2026). "Transformerに基づく逐次推薦モデルにおける自己注意重みの再考." 2026年度 人工知能学会全国大会 (JSAI).
Published in International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2026
Recommended citation: Keito Kozaki, Keigo Sakurai, Ren Togo, Takahiro Ogawa, Miki Haseyama. (2026). "Revisiting the Role of Learned Attention Weighting in SASRec." Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), pp. 3894-3899.
Published in ACM Conference on Recommender Systems (RecSys), 2026
Recommended citation: Keito Kozaki, Keigo Sakurai, Ren Togo, Takahiro Ogawa, Miki Haseyama. (2026). "Residual Dominance as a Structural Account of Last-Item Reliance in Causal Self-Attention Recommenders." Proceedings of the ACM Conference on Recommender Systems (RecSys).
Published in ACM International Conference on Information and Knowledge Management (CIKM), 2026
Recommended citation: Keito Kozaki, Keigo Sakurai, Ren Togo, Takahiro Ogawa, Miki Haseyama. (2026). "Diagnosing Lexical Text-Anchor Retrievability in Sequential Recommendation Benchmarks." Proceedings of the ACM International Conference on Information and Knowledge Management (CIKM).