77 citations
- Cornell UniversityUS3 papers
- Shibuya (Japan)JP2 papers
- Carnegie Mellon UniversityUS1 paper
- Hosei UniversityJP1 paper
- Kyushu UniversityJP1 paper
- Microsoft Research (United Kingdom)GB1 paper
- Microsoft (United States)US1 paper
- The Graduate University for Advanced Studies, SOKENDAIJP1 paper
- The University of OsakaJP1 paper
- The University of TokyoJP1 paper
- Toyohashi University of TechnologyJP1 paper
- University of ManitobaCA1 paper
6 papers · 1 filter
A Critical Reexamination of Intra-List Distance and Dispersion
Naoto Ohsaka, Riku Togashi
Diversification of recommendation results is a promising approach for coping with the uncertainty associated with users' information needs. Of particular importance in diversified…
Curse of "Low" Dimensionality in Recommender Systems
Naoto Ohsaka, Riku Togashi
Beyond accuracy, there are a variety of aspects to the quality of recommender systems, such as diversity, fairness, and robustness. We argue that many of the prevalent problems in…
Matching Theory-based Recommender Systems in Online Dating
Yoji Tomita, Riku Togashi, Daisuke Moriwaki
Online dating platforms provide people with the opportunity to find a partner. Recommender systems in online dating platforms suggest one side of users to the other side of users.…
A Real-World Implementation of Unbiased Lift-based Bidding System
Daisuke Moriwaki, Yuta Hayakawa, Akira Matsui +3
In display ad auctions of Real-Time Bid-ding (RTB), a typical Demand-Side Platform (DSP)bids based on the predicted probability of click and conversion right after an ad impression…
Density-Ratio Based Personalised Ranking from Implicit Feedback
Riku Togashi, Masahiro Kato, Mayu Otani +1
Learning from implicit user feedback is challenging as we can only observe positive samples but never access negative ones. Most conventional methods cope with this issue by adopti…
Alleviating Cold-Start Problems in Recommendation through Pseudo-Labelling over Knowledge Graph
Riku Togashi, Mayu Otani, Shin'ichi Satoh
Solving cold-start problems is indispensable to provide meaningful recommendation results for new users and items. Under sparsely observed data, unobserved user-item pairs are also…