Revisiting Recommendation Loss Functions through Contrastive Learning (Technical Report)
This work addresses recommendation system losses for researchers, but it is incremental as it builds on existing contrastive learning techniques.
The paper systematically examines recommendation losses and introduces InfoNCE+ and MINE+ as optimized contrastive learning methods, showing their effectiveness in improving performance.
Inspired by the success of contrastive learning, we systematically examine recommendation losses, including listwise (softmax), pairwise (BPR), and pointwise (MSE and CCL) losses. In this endeavor, we introduce InfoNCE+, an optimized generalization of InfoNCE with balance coefficients, and highlight its performance advantages, particularly when aligned with our new decoupled contrastive loss, MINE+. We also leverage debiased InfoNCE to debias pointwise recommendation loss (CCL) as Debiased CCL. Interestingly, our analysis reveals that linear models like iALS and EASE are inherently debiased. Empirical results demonstrates the effectiveness of MINE+ and Debiased-CCL.