EchoAlign: Bridging Generative and Discriminative Learning under Noisy Labels

ArXi:2405.12969v3 Announce Type: replace Noisy labels severely hinder the accuracy and generalization of machine learning models, especially when ambiguous instance features make reliable annotation difficult. Existing approaches, including transition-matrix-based label correction, struggle to capture complex relationships between instances and noisy labels, limiting their effectiveness in such settings. We present EchoAlign, a framework that bridges generative and discriminative learning under noisy labels.