structural heterogeneity
Structural heterogeneity refers to the diverse nature of data or model architectures, where different components exhibit distinct structures or characteristics. This variability can impact model performance and generalization capabilities.
- FedIGL: Federated Invariant Graph Learning for Non-IID Graphs
- Local-Global Associative Frames for Symmetry-Preserving Crystal Structure Modeling
- Multiscale guidance of protein structure prediction with heterogeneous cryo-EM data
- PMLF: A Physics-Guided Multiscale Loss Framework for Structurally Heterogeneous Time Series
- SMARTraj$^2$: A Stable Multi-City Adaptive Method for Multi-View Spatio-Temporal Trajectory Representation Learning