Learning the structure of auto-encoding recommenders

Farhan KHAWAR, Kin Man POON, Nevin L. ZHANG

Research output: Chapter in Book/Report/Conference proceedingChapters

16 Citations (Scopus)

Abstract

Autoencoder recommenders have recently shown state-of-the-art performance in the recommendation task due to their ability to model non-linear item relationships effectively. However, existing autoencoder recommenders use fully-connected neural network layers and do not employ structure learning. This can lead to inefficient training, especially when the data is sparse as commonly found in collaborative filtering. The aforementioned results in lower generalization ability and reduced performance. In this paper, we introduce structure learning for autoencoder recommenders by taking advantage of the inherent item groups present in the collaborative filtering domain. Due to the nature of items in general, we know that certain items are more related to each other than to other items. Based on this, we propose a method that first learns groups of related items and then uses this information to determine the connectivity structure of an auto-encoding neural network. This results in a network that is sparsely connected. This sparse structure can be viewed as a prior that guides the network training. Empirically we demonstrate that the proposed structure learning enables the autoencoder to converge to a local optimum with a much smaller spectral norm and generalization error bound than the fully-connected network. The resultant sparse network considerably outperforms the state-of-the-art methods like Mult-vae/Mult-dae on multiple benchmarked datasets even when the same number of parameters and flops are used. It also has a better cold-start performance. Copyright © 2020 IW3C2 (International World Wide Web Conference Committee), published under Creative Commons CC-BY 4.0 License.
Original languageEnglish
Title of host publicationProceedings of The World Wide Web Conference WWW 2020
EditorsYennun HUANG, Irwin KING, Tie-Yan LIU, Maarten VAN STEEN
Place of PublicationNew York
PublisherAssociation for Computing Machinery
Pages519-529
ISBN (Print)9781450370233
DOIs
Publication statusPublished - Apr 2020

Citation

Khawar, F., Poon, L., & Zhang, N. L. (2020). Learning the structure of auto-encoding recommenders. In Y. Huang, I. King, T.-Y. Liu, & M. van Steen (Eds.), Proceedings of The World Wide Web Conference WWW 2020 (pp. 519-529). New York: Association for Computing Machinery.

Keywords

  • Structure learning
  • Collaborative filtering
  • Sparse autoencoder
  • Wide autoencoder
  • Shallow networks

Fingerprint

Dive into the research topics of 'Learning the structure of auto-encoding recommenders'. Together they form a unique fingerprint.