Zhifeng Hao

SpectralMol: Spectral Graph Bisection Achieves Universal Molecular Fragment Decomposition for Drug-Like Molecule Generation

Generating valid, diverse, and drug-like molecules remains a central challenge in computational drug discovery. A key bottleneck for fragment-based generative models is decomposition coverage: existing junction-tree methods fail on bridged bicyclic and spiro ring systems common in drug-like scaffolds. Our primary con...

: Spectral Graph Bisection Achieves Universal Molecular Fragment Decomposition for Drug-Like Molecule Generation

PrePrompt: Predictive Prompting for Class Incremental Learning

Prompt-based learning has emerged as a promising paradigm for Class Incremental Learning (CIL), enabling pre-trained models to adapt efficiently to open-world scenarios. Existing methods often employ correlation-based strategies, where an image's feature serves as a query to retrieve the most relevant key prompts, with...

DHMNN: A Hypergraph Motif-Based Framework for Directed Hyperlink Prediction.

A novel directed hypergraph motif-based neural network (DHMNN) for directed hyperlink prediction, which simultaneously captures higher order structural and connectivity information from the directed hypergraph topology and significantly outperforms state-of-the-art models.