Graph Neural Networks

[Nature Machine Intelligence, 2024] This paper introduces PSICHIC, a graph neural network framework that leverages physicochemical constraints to predict protein-ligand interactions directly from sequence data. PSICHIC achieves state-of-the-art accuracy in binding affinity prediction, even surpassing existing structure-based methods in certain cases. Furthermore, its interpretable fingerprints illuminate the specific protein residues and ligand atoms involved in these interactions, offering a promising tool for virtual screening and enhancing our understanding of protein-ligand mechanisms.

[PIEEE, 2024] This paper discusses the growing relevance of graph neural networks (GNNs) across various real-world applications, from recommendation systems to drug discovery, emphasizing the need for trustworthy GNNs beyond task performance. The survey proposes a comprehensive roadmap for building such GNNs, addressing six key aspects: robustness, explainability, privacy, fairness, accountability, and environmental well-being. Additionally, it highlights the interrelations among these aspects and presents future directions for advancing trustworthy GNN research and its industrial applications.

Active learning (AL), that aims to label limited data samples to effectively train the model, stands as a very cost-effective data …

Evaluating the performance of a well-trained GNN model on real-world graphs is a pivotal step for reliable GNN online deployment and …

[ICLR-2024] This work introduces Time-LLM, a novel reprogramming framework that adapts Large Language Models (LLMs) for general time series forecasting, overcoming the challenges of data sparsity and modality alignment between time series and natural language. By reprogramming time series data with text prototypes and employing the Prompt-as-Prefix (PaP) technique for enriched input context, Time-LLM demonstrates superior forecasting performance, outshining specialized models in both few-shot and zero-shot learning scenarios.

Graph neural networks (GNNs) have gained significant attraction due to their expansive real-world applications. To build trustworthy …

Graph neural networks (GNNs) have a powerful ability to capture long-range spatial correlations in hyperspectral images (HSIs). …

The great learning ability of deep learning facilitates us to comprehend the real physical world, making learning to simulate …