A Related Work
–Neural Information Processing Systems
The latest CL-based CF methods can roughly fall into two research lines. The second category, referred to as "loss-based" approaches, The prevailing augmentation-based paradigm in CL-based CF methods is to employ user-item bipartite graph augmentations to generate contrasting views. Despite the remarkable success of CL-based CF methods, there remains a lack of theoretical understanding, particularly regarding the superior generalization ability of contrastive loss. B.4 Align T op-K evaluation metric Discounted Cumulative Gain (DCG) is a commonly used ranking metric in top-K recommendation In DCG, the relevance of an item's contribution to the utility decreases logarithmically in relation to its position in the ranked list. The training set is comprised of 311,704 user-selected ratings ranging from 1 to 5. The test set includes ratings for ten songs randomly exposed to each user.
Neural Information Processing Systems
Oct-8-2025, 04:07:39 GMT