Curriculum Vitae

Kai Sugahara

簀河原 皆

Profiles

Research

Writing

Social

Contact

Email address

Based on Minimal for GitHub Pages.

Experience

– Present

Machine Learning Engineer — AdTech

MicroAd, Inc.
Shibuya, Tokyo, Japan

Education

April 2022 – March 2024

Master of Engineering

Department of Informatics
University of Electro-Communications
Tokyo, Japan

UEC Student Award

April 2018 – March 2022

Bachelor of Engineering

Department of Informatics
University of Electro-Communications
Tokyo, Japan

Publications

International Conference

  1. Kai Sugahara: Towards Dynamic Relationship Schema Discovery for Complementary News Recommendation, In: Proceedings of the 20th ACM Conference on Recommender Systems (RecSys '26), 1767–1769, 2026. Paper
  2. Chihiro Yamasaki, Kai Sugahara, Kazushi Okamoto: Knowledge-Augmented Relation Learning for Complementary Recommendation with Large Language Models, In: Proceedings of the second workshop on Generative AI for E-Commerce (@RecSys '25), 2025. Paper arXiv
  3. Kai Sugahara, Chihiro Yamasaki, Kazushi Okamoto: Is It Really Complementary? Revisiting Behavior-based Labels for Complementary Recommendation, In: Proceedings of the 18th ACM Conference on Recommender Systems (RecSys '24), 1091-1095, 2024. Paper Post-conference paper presentation (in Japanese) — RecSys2024 論文読み会、
  4. Kai Sugahara, Kazushi Okamoto: Keyword-based Research Field Discovery with External Knowledge Aware Hierarchical Co-clustering, In: Advanced Computational Intelligence and Intelligent Informatics, 153-166, 2024. Paper Session Best Presentation Award

Journal

  1. Chihiro Yamasaki, Kai Sugahara, Yuma Nagi, Kazushi Okamoto: Function-based Labels for Complementary Recommendation: Definition, Annotation, and LLM-as-a-Judge, Pattern Recognition Letters, 200, 8-15, 2026. Paper arXiv
  2. Kai Sugahara, Kazushi Okamoto: Hierarchical Matrix Factorization for Interpretable Collaborative Filtering, Pattern Recognition Letters, 180, 99-106, 2024. Paper arXiv
  3. Kai Sugahara, Kazushi Okamoto: Hierarchical Co-clustering with Augmented Matrices from External Domains, Pattern Recognition, 142, 109657, 2023. Paper

Domestic Conference (in Japanese)

  1. 簀河原 皆, 山﨑 千寛, 梛木 佑真, 岡本 一志: アイテムの機能関係に注目した補完推薦に関する検討, 電子情報通信学会 技術研究報告, 2024. Paper

Japanese Patent (in Japanese)

  1. 簀河原 皆、岡本 一志：情報処理装置および情報処理方法、並びにプログラム。特許第7807042号（日本、登録日：）。特許権者：国立大学法人電気通信大学。J-GLOBAL