Welcome to the 46th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2023), taking place in Taipei, Taiwan, from July 23-27, 2023.
As the premier scientific conference in the expansive field of information retrieval, SIGIR 2023 is thoughtfully organized as a hybrid event in the aftermath of the COVID-19 pandemic. While we strongly advocate for in-person participation, we also offer virtual attendance options. This arrangement not only contributes to reducing carbon footprints but also mitigates travel complexities for individuals from certain regions. Furthermore, this edition sets a significant milestone not only for its traditional and innovative tracks, but also as a response to the SIGIR Executive Committee's prompt to actively integrate sustainable development considerations into its organization and implementation. In a pioneering attempt to incorporate the theme of sustainability, SIGIR 2023 is carrying out a carbon emissions survey, hoping it can serve as a reference for subsequent conferences.
Adaptive Popularity Debiasing Aggregator for Graph Collaborative Filtering
The graph neural network-based collaborative filtering (CF) models user-item interactions as a bipartite graph and performs iterative aggregation to enhance performance. Unfortunately, the aggregation process may amplify the popularity bias, which ...
On the Impact of Outlier Bias on User Clicks
User interaction data is an important source of supervision in counterfactual learning to rank (CLTR). Such data suffers from presentation bias. Much work in unbiased learning to rank (ULTR) focuses on position bias, i.e., items at higher ranks are more ...
Rectifying Unfairness in Recommendation Feedback Loop
The issue of fairness in recommendation systems has recently become a matter of growing concern for both the academic and industrial sectors due to the potential for bias in machine learning models. One such bias is that of feedback loops, where the ...
Contrastive Box Embedding for Collaborative Reasoning
Most of the existing personalized recommendation methods predict the probability that one user might interact with the next item by matching their representations in the latent space. However, as a cognitive task, it is essential for an impressive ...
Learning to Re-rank with Constrained Meta-Optimal Transport
Many re-ranking strategies in search systems rely on stochastic ranking policies, encoded as Doubly-Stochastic (DS) matrices, that satisfy desired ranking constraints in expectation, e.g., Fairness of Exposure (FOE). These strategies are generally two-...
Cited By
- Formal T, Clinchant S, Déjean H and Lassance C SPLATE: Sparse Late Interaction Retrieval Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, (2635-2640)
- Kato M, Mothe J and Poblete B (2024). Report on the 46th ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2023): Reflections from the Program Co-Chairs, ACM SIGIR Forum, 57:2, (1-20), Online publication date: 1-Dec-2023.
Index Terms
- Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval