Dataset Condensation for Recommendation

TL;DR

This paper introduces DConRec, a novel dataset condensation framework for recommendation systems that synthesizes small, informative datasets by modeling discrete user-item interactions and incorporating user preferences, resulting in efficient training.

Contribution

The paper presents a lightweight, probabilistic condensation method tailored for recommendation datasets, addressing limitations of existing approaches in generating discrete interactions and preserving preferences.

Findings

Effective in synthesizing small, informative datasets

Accelerates data synthesis with lightweight policy gradient

Demonstrates superior performance on real-world datasets

Abstract

Training recommendation models on large datasets requires significant time and resources. It is desired to construct concise yet informative datasets for efficient training. Recent advances in dataset condensation show promise in addressing this problem by synthesizing small datasets. However, applying existing methods of dataset condensation to recommendation has limitations: (1) they fail to generate discrete user-item interactions, and (2) they could not preserve users' potential preferences. To address the limitations, we propose a lightweight condensation framework tailored for recommendation (DConRec), focusing on condensing user-item historical interaction sets. Specifically, we model the discrete user-item interactions via a probabilistic approach and design a pre-augmentation module to incorporate the potential preferences of users into the condensed datasets. While the substantial size of datasets leads to costly optimization, we propose a lightweight policy gradient estimation to accelerate the data synthesis. Experimental results on multiple real-world datasets have demonstrated the effectiveness and efficiency of our framework. Besides, we provide a theoretical analysis of the provable convergence of DConRec. Our implementation is available at: https://github.com/JiahaoWuGit/DConRec.