Loading [a11y]/accessibility-menu.js
Condensing Pre-Augmented Recommendation Data via Lightweight Policy Gradient Estimation | IEEE Journals & Magazine | IEEE Xplore

Condensing Pre-Augmented Recommendation Data via Lightweight Policy Gradient Estimation


Abstract:

Training recommendation models on large datasets requires significant time and resources. It is desired to construct concise yet informative datasets for efficient traini...Show More

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.
Published in: IEEE Transactions on Knowledge and Data Engineering ( Volume: 37, Issue: 1, January 2025)
Page(s): 162 - 173
Date of Publication: 22 October 2024

ISSN Information:

Funding Agency:


References

References is not available for this document.