Abstract
Graph neural networks combined with comparative learning have become a very popular paradigm in recommender systems. However, most methods still suffer from data sparsity, noise and difficulty in extracting multi-granularity information. To address these limitations, we propose a Dual Representation Propagation Comparative Learning(DRPCL) method, which uses propagation representations based on two rules to extract multi-granularity signals, including graph convolutional propagation pathway and message node propagation pathway. Where the message node propagation pathway extracts and integrates local and global signals. And the dual-pathway node representations generate misaligned contrastive views and denoising auxiliary supervision signals to mitigate the negative effects of data sparsity and noise. Experimental results show that our DRPCL is able to demonstrate performance superiority over other bases on different datasets. Some in-depth experimental analysis demonstrates the robustness of DRPCL against data sparsity and noise.