2024/03/19 by Yifei Wang, Qi Zhang, Wang, Yifei +5 · 1 citation
Psychology · Social Sciences · #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #Early Childhood Education and Development #Emotional Intelligence and Performance #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Psychological and Educational Research Studies
paper · pdf · doi:10.48550/arxiv.2403.12459
openalex publication_date 2024/03/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Deep representations have shown promising performance when transferred to downstream tasks in a black-box manner. Yet, their inherent lack of interpretability remains a significant challenge, as these features are often opaque to human understanding. In this paper, we propose Non-negative Contrastive Learning (NCL), a renaissance of Non-negative Matrix Factorization (NMF) aimed at deriving interpretable features. The power of NCL lies in its enforcement of non-negativity constraints on features, reminiscent of NMF's capability to extract features that align closely with sample clusters. NCL not only aligns mathematically well with an NMF objective but also preserves NMF's interpretability attributes, resulting in a more sparse and disentangled representation compared to standard contrastive learning (CL). Theoretically, we establish guarantees on the identifiability and downstream generalization of NCL. Empirically, we show that these advantages enable NCL to outperform CL significantly on feature disentanglement, feature selection, as well as downstream classification tasks. At last, we show that NCL can be easily extended to other learning scenarios and benefit supervised learning as well. Code is available at https://github.com/PKU-ML/nonneg.