Distributed Recommendation Systems: Survey and Research Directions

Q Cai, J Cao, G Xu, N Zhu - ACM Transactions on Information Systems, 2024 - dl.acm.org
With the explosive growth of online information, recommendation systems have become
essential tools for alleviating information overload. In recent years, researchers have …

Efficient and deployable knowledge infusion for open-world recommendations via large language models

Y **, W Liu, J Lin, M Weng, X Cai, H Zhu, J Zhu… - arxiv preprint arxiv …, 2024 - arxiv.org
Recommender systems (RSs) play a pervasive role in today's online services, yet their
closed-loop nature constrains their access to open-world knowledge. Recently, large …

An Automatic Graph Construction Framework based on Large Language Models for Recommendation

R Shan, J Lin, C Zhu, B Chen, M Zhu, K Zhang… - arxiv preprint arxiv …, 2024 - arxiv.org
Graph neural networks (GNNs) have emerged as state-of-the-art methods to learn from
graph-structured data for recommendation. However, most existing GNN-based …

A decoding acceleration framework for industrial deployable LLM-based recommender systems

Y **, H Wang, B Chen, J Lin, M Zhu, W Liu… - arxiv preprint arxiv …, 2024 - arxiv.org
Recently, increasing attention has been paid to LLM-based recommender systems, but their
deployment is still under exploration in the industry. Most deployments utilize LLMs as …

Pareto-based multi-objective recommender system with forgetting curve

J **, Z Zhang, Z Li, X Gao, X Yang, L **ao… - Proceedings of the 33rd …, 2024 - dl.acm.org
Recommender systems with cascading architecture play an increasingly significant role in
online recommendation platforms, where the approach to dealing with negative feedback is …

Utility-oriented Reranking with Counterfactual Context

Y **, W Liu, X Dai, R Tang, Q Liu, W Zhang… - ACM Transactions on …, 2024 - dl.acm.org
As a critical task for large-scale commercial recommender systems, reranking rearranges
items in the initial ranking lists from the previous ranking stage to better meet users' …

Forward Once for All: Structural Parameterized Adaptation for Efficient Cloud-coordinated On-device Recommendation

K Fu, Z Lv, S Zhang, F Wu, K Kuang - arxiv preprint arxiv:2501.02837, 2025 - arxiv.org
In cloud-centric recommender system, regular data exchanges between user devices and
cloud could potentially elevate bandwidth demands and privacy risks. On-device …

Beyond Positive History: Re-ranking with List-level Hybrid Feedback

M Weng, Y **, W Liu, B Chen, J Lin, R Tang… - arxiv preprint arxiv …, 2024 - arxiv.org
As the last stage of recommender systems, re-ranking generates a re-ordered list that aligns
with the user's preference. However, previous works generally focus on item-level positive …

HiFI: Hierarchical Fairness-aware Integrated Ranking with Constrained Reinforcement Learning

Y Liu, W **a, W Liu, M Zhu, W Zhang, R Tang… - … Proceedings of the ACM …, 2024 - dl.acm.org
Integrated ranking is a critical component in industrial recommendation platforms. It
combines candidate lists from different upstream channels or sources and ranks them into …

Multi-sourced Integrated Ranking with Exposure Fairness

Y Liu, W Liu, W **a, J Zhu, W Zhang, Z Dong… - Pacific-Asia Conference …, 2024 - Springer
Integrated ranking system is one of the critical components of industrial recommendation
platforms. An integrated ranking system is expected to generate a mix of heterogeneous …