Task-Aware Retrieval Augmentation for Dynamic Recommendation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tao, Zhen, Jiang, Xinke, Feng, Qingshuai, Zhang, Haoyu, Du, Lun, Fang, Yuchen, Miao, Hao, Xie, Bangquan, Sun, Qingqiang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915621031116800
author Tao, Zhen
Jiang, Xinke
Feng, Qingshuai
Zhang, Haoyu
Du, Lun
Fang, Yuchen
Miao, Hao
Xie, Bangquan
Sun, Qingqiang
author_facet Tao, Zhen
Jiang, Xinke
Feng, Qingshuai
Zhang, Haoyu
Du, Lun
Fang, Yuchen
Miao, Hao
Xie, Bangquan
Sun, Qingqiang
contents Dynamic recommendation systems aim to provide personalized suggestions by modeling temporal user-item interactions across time-series behavioral data. Recent studies have leveraged pre-trained dynamic graph neural networks (GNNs) to learn user-item representations over temporal snapshot graphs. However, fine-tuning GNNs on these graphs often results in generalization issues due to temporal discrepancies between pre-training and fine-tuning stages, limiting the model's ability to capture evolving user preferences. To address this, we propose TarDGR, a task-aware retrieval-augmented framework designed to enhance generalization capability by incorporating task-aware model and retrieval-augmentation. Specifically, TarDGR introduces a Task-Aware Evaluation Mechanism to identify semantically relevant historical subgraphs, enabling the construction of task-specific datasets without manual labeling. It also presents a Graph Transformer-based Task-Aware Model that integrates semantic and structural encodings to assess subgraph relevance. During inference, TarDGR retrieves and fuses task-aware subgraphs with the query subgraph, enriching its representation and mitigating temporal generalization issues. Experiments on multiple large-scale dynamic graph datasets demonstrate that TarDGR consistently outperforms state-of-the-art methods, with extensive empirical evidence underscoring its superior accuracy and generalization capabilities.
format Preprint
id arxiv_https___arxiv_org_abs_2511_12495
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Task-Aware Retrieval Augmentation for Dynamic Recommendation
Tao, Zhen
Jiang, Xinke
Feng, Qingshuai
Zhang, Haoyu
Du, Lun
Fang, Yuchen
Miao, Hao
Xie, Bangquan
Sun, Qingqiang
Information Retrieval
Social and Information Networks
Dynamic recommendation systems aim to provide personalized suggestions by modeling temporal user-item interactions across time-series behavioral data. Recent studies have leveraged pre-trained dynamic graph neural networks (GNNs) to learn user-item representations over temporal snapshot graphs. However, fine-tuning GNNs on these graphs often results in generalization issues due to temporal discrepancies between pre-training and fine-tuning stages, limiting the model's ability to capture evolving user preferences. To address this, we propose TarDGR, a task-aware retrieval-augmented framework designed to enhance generalization capability by incorporating task-aware model and retrieval-augmentation. Specifically, TarDGR introduces a Task-Aware Evaluation Mechanism to identify semantically relevant historical subgraphs, enabling the construction of task-specific datasets without manual labeling. It also presents a Graph Transformer-based Task-Aware Model that integrates semantic and structural encodings to assess subgraph relevance. During inference, TarDGR retrieves and fuses task-aware subgraphs with the query subgraph, enriching its representation and mitigating temporal generalization issues. Experiments on multiple large-scale dynamic graph datasets demonstrate that TarDGR consistently outperforms state-of-the-art methods, with extensive empirical evidence underscoring its superior accuracy and generalization capabilities.
title Task-Aware Retrieval Augmentation for Dynamic Recommendation
topic Information Retrieval
Social and Information Networks
url https://arxiv.org/abs/2511.12495