Riku Togashi
Email: rtogashi (at) acm.org
Google Scholar author ID: KVEf0M4AAAAJ
DBLP: 198/5462

I am a member of CyberAgent, Inc. AI Lab, where I work on recommender systems. My research interests lie at the scalability and robustness of methods/measures for recommender systems and information retrieval.

Research Interests:
  • Scalable methods for item recommendation
  • Distributed optimization of complex objectives/models
Selected Publications:
Safe Collaborative Filtering
Riku Togashi, Tatsushi Oka, Naoto Ohsaka, Tetsuro Morimura
ICLR'24 [paper]
Scalable and Provably Fair Exposure Control for Large-Scale Recommender Systems
Riku Togashi, Kenshi Abe, Yuta Saito
WWW'24 [paper (coming soon)]
Fast and Examination-agnostic Reciprocal Recommendation in Matching Markets
Yoji Tomita, Riku Togashi, Yuriko Hashizume, Naoto Ohsaka
RecSys'23 [paper]
Curse of "Low" Dimensionality in Recommener Systems
Naoto Ohsaka, Riku Togashi (equal contribution)
SIGIR'23 [paper]
A Critical Reexamination of Intra-List Distance and Dispersion
Naoto Ohsaka, Riku Togashi
SIGIR'23 [paper]
Toward Verifiable and Reproducible Human Evaluation for Text-to-Image Generation
Mayu Otani, Riku Togashi, Yu Sawai, Ryosuke Ishigami, Yuta Nakashima, Esa Rahtu, Janne Heikkilä, Shin'ichi Satoh
CVPR'23 [paper]
Matching-Theory-Based Recommender Systems for Online Dating
Yoji Tomita, Riku Togashi, Daisuke Moriwaki
RecSys'22 Industrial Talk [paper]
AxIoU: Axiomatically Justified Measure for Video Moment Retrieval
Riku Togashi, Otani Mayu, Yuta Nakashima, Esa Rahtu, Janne Heikkila, Tetsuya Sakai
CVPR'22 [paper]
Optimal Correction Cost for Object Detection Evaluation
Otani Mayu, Riku Togashi, Yuta Nakashima, Esa Rahtu, Janne Heikkila, Shin'ichi Satoh
CVPR'22 [paper]
Scalable Personalised Item Ranking through Parametric Density Estimation
Riku Togashi, Masahiro Kato, Otani Mayu, Shin'ichi Satoh, Tetsuya Sakai
SIGIR'21 [paper]
Density-Ratio Based Personalised Ranking from Implicit Feedback
Riku Togashi, Masahiro Kato, Otani Mayu, Shin'ichi Satoh
WWW'21 [paper]
Alleviating Cold-Start Problems in Recommendation through Pseudo-Labelling over Knowledge Graph
Riku Togashi, Mayu Otani, Shin'ichi Satoh
WSDM'21 [paper]
Preprints:
Awards:
  • Database Society of Japan, Kambayashi Young Researcher Award