• Corpus ID: 235755396

SelfCF: A Simple Framework for Self-supervised Collaborative Filtering

@article{Zhou2021SelfCFAS,
  title={SelfCF: A Simple Framework for Self-supervised Collaborative Filtering},
  author={Xin Zhou and Aixin Sun and Yong Liu and Jie Zhang and Chunyan Miao},
  journal={ArXiv},
  year={2021},
  volume={abs/2107.03019}
}

• Xin Zhou, Aixin Sun, +2 authors C. Miao
• Published 7 July 2021
• Computer Science
• ArXiv

Collaborative filtering (CF) is widely used to learn informative latent representations of users and items from observed interactions. Existing CF-based methods commonly adopt negative sampling to discriminate different items. That is, observed user-item pairs are treated as positive instances; unobserved pairs are considered as negative instances and are sampled under a defined distribution for training. Training with negative sampling on large datasets is computationally expensive. Further, negative items should be carefully sampled under the defined distribution, in order to avoid selecting an observed positive item in the training dataset. Unavoidably, some negative items sampled from the training dataset could be positive in the test set. Recently, self-supervised learning (SSL) has emerged as a powerful tool to learn a model without negative samples. In this paper, we propose a self-supervised collaborative filtering framework (SelfCF), that is specially designed for recommender scenario with implicit feedback. The proposed SelfCF framework simplifies the Siamese networks and can be easily applied to existing deep-learning based CF models, which we refer to as backbone networks. The main idea of SelfCF is to augment the output embeddings generated by backbone networks, because it is infeasible to augment raw input of user/item ids. We propose and study three output perturbation techniques that can be applied to different types of backbone networks including both traditional CF models and graph-based models. The framework enables learning informative representations of users and items without negative samples, and is agnostic to the encapsulated backbones. We conduct comprehensive experiments on four datasets to show that our framework may achieve even better recommendation accuracy than the encapsulated supervised counterpart with a 2 × –4 × faster training speed. We also show that SelfCF can boost up the accuracy by up to 17.79% on average, compared with a self-supervised framework BUIR. coefficient. We set both the momentum of SelfCF he and the dropout of SelfCF ed value in the range of [0.1, 0.6] with a step of 0.1. The 𝐿 2 regularization coefficient 𝜆 1 is searched in the range of {0.0, 1e-05, 1e-04, ..., 1e-01}. We plot the heatmap for SelfCF he , SelfCF ed , SelfCF ep over Recall@20 and NDCG@20 in Fig. 6 and Fig. 7, respectively.