SAHC-NS: Structure-Aware and Hardness-Calibrated Negative Sampling for Implicit Collaborative Filtering
2026-08-17 • Information Retrieval
Information Retrieval
AI summaryⓘ
The authors address a problem in recommendation systems where picking 'negative' examples (things users don’t like) is important but tricky. Current methods often treat all users the same way and only look at simple scores between users and items. The authors propose SAHC-NS, a new way that looks at detailed structural information in the data and adjusts how hard or informative the negative examples are depending on the user. Their method aims to pick better negative samples for training recommenders and performs better in tests.
Negative samplingCollaborative filteringImplicit feedbackRecommendation systemsUser-item embeddingsNeighborhood aggregationHardness calibrationStructural discrepancyNegative augmentationMulti-hop aggregation
Authors
Jiayi Wu, Zhengyu Wu, Xunkai Li, Hongchao Qin, Rong-Hua Li, Guoren Wang
Abstract
Negative sampling is a key component of implicit collaborative filtering (CF), as it enables recommenders to effectively learn user preferences. Existing negative sampling methods mostly follow a two-stage paradigm: they first construct a candidate negative pool for each user and then select negative samples from the pool according to predefined sampling rules. However, these methods usually overlook the hardness variation of candidate negative pools across users, making it difficult to adaptively adjust the hardness and informativeness of negative samples according to candidate-pool conditions. In addition, most existing samplers evaluate candidate negatives mainly through a matching score computed from the final aggregated user and item embeddings, while ignoring the structural differences captured by multi-hop neighborhood aggregation. As a result, the training value of negatives may be insufficiently characterized. To address these issues, we propose SAHC-NS, a Structure-Aware and Hardness-Calibrated Negative Sampling method. Specifically, SAHC-NS uses the mean and standard deviation of layer-wise matching scores to capture the overall matching strength and cross-layer structural discrepancy of candidate negatives, respectively. This enables SAHC-NS to select informative negatives by taking cross-layer structural discrepancy into account, rather than relying solely on final matching scores. Moreover, SAHC-NS introduces a candidate-pool-aware hardness calibration module to dynamically adjust negative augmentation strength according to candidate-pool hardness, producing hardness-controllable negatives. Extensive experiments demonstrate the superiority of SAHC-NS over existing negative sampling methods.