Debiased Pairwise Learning from Positive-Unlabeled Implicit Feedback

Learning contrastive representations from pairwise comparisons has achieved remarkable success in various fields, such as natural language processing, computer vision, and information retrieval. Collaborative filtering algorithms based on pairwise learning also rooted in this paradigm. A significant concern is the absence of labels for negative instances in implicit feedback data, which often results in the random selected negative instances contains false negatives and inevitably, biased embeddings. To address this issue, we introduce a novel correction method for sampling bias that yields a modified loss for pairwise learning called debiased pairwise loss (DPL). The key idea underlying DPL is to correct the biased probability estimates that result from false negatives, thereby correcting the gradients to approximate those of fully supervised data. The implementation of DPL only requires a small modification of the codes. Experimental studies on five public datasets validate the effectiveness of proposed learning method.