Out-of-domain (OOD) generalization is a significant challenge for machine learning models.

Similar yet distinct, hypergraph-based methods employ the hypergraph structure toobtain entity representations using thecomplexfeature aggregation strategy.

However, the current MIL methods are usually based on independent and identical distribution hypothesis, thus neglect the correlation among different instances. To address this problem, we proposed a new framework, called correlated MIL, and provided a proof for convergence. Based on this framework, we devised a Transformer based MIL (TransMIL), which explored both morphological and spatial information. The proposed TransMIL can effectively deal with unbalanced/balanced and binary/multiple classification with great visualization and interpretability.

Sharpness-Aware Minimization (SAM) has attracted significant attention for its effectiveness in improving generalization across various tasks. However, its underlying principles remain poorly understood.

The nature of structured models is that communication among the components has a bottleneck, typically achieved by restricted connectivity and attention.