Model-Agnostic Dual-Side Online Fairness Learning for Dynamic Recommendation
- 21 February 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 37 (5) , 2727-2742
Abstract
Fairness in recommendation has drawn much attention since it significantly affects how users access information and how information is exposed to users. However, most fairness-aware methods are designed offline with the entire stationary interaction data to handle the global unfairness issue and evaluate their performance in a one-time paradigm. In real-world scenarios, users tend to interact with items continuously over time, leading to a dynamic recommendation environment where unfairness is evolving online. Moreover, previous methods that focus on mitigating the unfairness can hardly bring significant improvements to the recommendation task. Hence, in this paper, we propose a Model-agnostic Dual-side Online Fairness Learning method (MDOFair) for the dynamic recommendation. First, we carefully design dynamic dual-side fairness learning to trace the rapid evolution of unfairness from both the user and item sides. Second, we leverage the fairness and recommendation tasks in one utilized framework to pursue the double-win success. Last, we present an efficient model-agnostic post-ranking method for the dynamic recommendation scenario to mitigate the dynamic unfairness while improving the recommendation performance significantly. Extensive experiments demonstrate the superiority and effectiveness of our proposed MDOFair by incorporating it into existing dynamic models as a post-ranking stageKeywords
Funding Information
- Hong Kong Research Grants Council (15200021)
- Australian Research Council (DP220103717, LE220100078)
- National Natural Science Foundation of China (62072257)
This publication has 46 references indexed in Scilit:
- Dynamic Multi-Objective Optimization Framework With Interactive Evolution for Sequential RecommendationIEEE Transactions on Emerging Topics in Computational Intelligence, 2023
- De-Biasing user conformity bias and item popularity bias in Group recommendation2023
- FAGR: Fairness-aware Group Recommendation in Event-based Social Networks2022
- Neu-PCM: Neural-based potential correlation mining for POI recommendationApplied Intelligence, 2022
- FaiRIR: Mitigating Exposure Bias From Related Item Recommendations in Two-Sided PlatformsIEEE Transactions on Computational Social Systems, 2022
- User-Item Matching for Recommendation FairnessIEEE Access, 2021
- Time-capturing Dynamic Graph Embedding for Temporal Linkage EvolutionIEEE Transactions on Knowledge and Data Engineering, 2021
- A flexible framework for evaluating user and item fairness in recommender systemsUser Modeling and User-Adapted Interaction, 2021
- Dynamic Graph Collaborative Filtering2020
- Eventera: Real-Time Event Recommendation System from Massive Heterogeneous Online Media2014