Task-Aware Retrieval Augmentation for Dynamic Recommendation

TL;DR

This paper introduces TarDGR, a retrieval-augmented framework for dynamic recommendation systems that improves generalization by incorporating task-aware subgraph retrieval and modeling, leading to better personalization over time.

Contribution

The paper proposes a novel task-aware retrieval-augmented approach with a graph transformer model to enhance temporal generalization in dynamic recommendation systems.

Findings

TarDGR outperforms state-of-the-art methods on large-scale datasets.

The task-aware evaluation mechanism effectively identifies relevant historical subgraphs.

Retrieving and fusing task-specific subgraphs improves recommendation accuracy.

Abstract

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.