Dual Adversarial Perturbators Generate rich Views for Recommendation
This work addresses a stability issue in graph-based recommender systems, offering an incremental improvement for enhancing model robustness in sparse data scenarios.
The paper tackles the risk of performance degradation or training collapse in graph contrastive learning for recommender systems when contrastive view differences are too large, by proposing AvoGCL, a dual-adversarial approach that progressively increases view difficulty, achieving significant outperformance over state-of-the-art methods on three real-world datasets.
Graph contrastive learning (GCL) has been extensively studied and leveraged as a potent tool in recommender systems. Most existing GCL-based recommenders generate contrastive views by altering the graph structure or introducing perturbations to embedding. While these methods effectively enhance learning from sparse data, they risk performance degradation or even training collapse when the differences between contrastive views become too pronounced. To mitigate this issue, we employ curriculum learning to incrementally increase the disparity between contrastive views, enabling the model to gain from more challenging scenarios. In this paper, we propose a dual-adversarial graph learning approach, AvoGCL, which emulates curriculum learning by progressively applying adversarial training to graph structures and embedding perturbations. Specifically, AvoGCL construct contrastive views by reducing graph redundancy and generating adversarial perturbations in the embedding space, and achieve better results by gradually increasing the difficulty of contrastive views. Extensive experiments on three real-world datasets demonstrate that AvoGCL significantly outperforms the state-of-the-art competitors.