Collaborative Filtering with User-Item Co-Autoregressive Models

Chao Du, Chongxuan Li, Yin Zheng, Jun Zhu, Bo Zhang

AAAI 2018 pp. 2175-2182

doi:10.1609/AAAI.V32I1.11884 /aaai/2018/du2018aaai-collaborative/

Abstract

Deep neural networks have shown promise in collaborative filtering (CF). However, existing neural approaches are either user-based or item-based, which cannot leverage all the underlying information explicitly. We propose CF-UIcA, a neural co-autoregressive model for CF tasks, which exploits the structural correlation in the domains of both users and items. The co-autoregression allows extra desired properties to be incorporated for different tasks. Furthermore, we develop an efficient stochastic learning algorithm to handle large scale datasets. We evaluate CF-UIcA on two popular benchmarks: MovieLens 1M and Netflix, and achieve state-of-the-art performance in both rating prediction and top-N recommendation tasks, which demonstrates the effectiveness of CF-UIcA.

PDF AAAI Semantic Scholar

Cite

Text

Du et al. "Collaborative Filtering with User-Item Co-Autoregressive Models." AAAI Conference on Artificial Intelligence, 2018. doi:10.1609/AAAI.V32I1.11884

Markdown

[Du et al. "Collaborative Filtering with User-Item Co-Autoregressive Models." AAAI Conference on Artificial Intelligence, 2018.](https://mlanthology.org/aaai/2018/du2018aaai-collaborative/) doi:10.1609/AAAI.V32I1.11884

BibTeX

@inproceedings{du2018aaai-collaborative,
  title     = {{Collaborative Filtering with User-Item Co-Autoregressive Models}},
  author    = {Du, Chao and Li, Chongxuan and Zheng, Yin and Zhu, Jun and Zhang, Bo},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2018},
  pages     = {2175-2182},
  doi       = {10.1609/AAAI.V32I1.11884},
  url       = {https://mlanthology.org/aaai/2018/du2018aaai-collaborative/}
}