Picture for Hongyang Gao

Hongyang Gao

G2T-LLM: Graph-to-Tree Text Encoding for Molecule Generation with Fine-Tuned Large Language Models

Add code
Oct 03, 2024
Viaarxiv icon

MAGE: Model-Level Graph Neural Networks Explanations via Motif-based Graph Generation

Add code
May 21, 2024
Viaarxiv icon

Inferring Data Preconditions from Deep Learning Models for Trustworthy Prediction in Deployment

Add code
Jan 26, 2024
Viaarxiv icon

MotifPiece: A Data-Driven Approach for Effective Motif Extraction and Molecular Representation Learning

Add code
Dec 24, 2023
Viaarxiv icon

Wide Neural Networks as Gaussian Processes: Lessons from Deep Equilibrium Models

Add code
Oct 16, 2023
Figure 1 for Wide Neural Networks as Gaussian Processes: Lessons from Deep Equilibrium Models
Figure 2 for Wide Neural Networks as Gaussian Processes: Lessons from Deep Equilibrium Models
Figure 3 for Wide Neural Networks as Gaussian Processes: Lessons from Deep Equilibrium Models
Figure 4 for Wide Neural Networks as Gaussian Processes: Lessons from Deep Equilibrium Models
Viaarxiv icon

DeepDFA: Dataflow Analysis-Guided Efficient Graph Learning for Vulnerability Detection

Add code
Dec 15, 2022
Viaarxiv icon

On the optimization and generalization of overparameterized implicit neural networks

Add code
Sep 30, 2022
Figure 1 for On the optimization and generalization of overparameterized implicit neural networks
Viaarxiv icon

Gradient Descent Optimizes Infinite-Depth ReLU Implicit Networks with Linear Widths

Add code
May 16, 2022
Figure 1 for Gradient Descent Optimizes Infinite-Depth ReLU Implicit Networks with Linear Widths
Figure 2 for Gradient Descent Optimizes Infinite-Depth ReLU Implicit Networks with Linear Widths
Figure 3 for Gradient Descent Optimizes Infinite-Depth ReLU Implicit Networks with Linear Widths
Figure 4 for Gradient Descent Optimizes Infinite-Depth ReLU Implicit Networks with Linear Widths
Viaarxiv icon

Molecular Graph Representation Learning via Heterogeneous Motif Graph Construction

Add code
Feb 01, 2022
Figure 1 for Molecular Graph Representation Learning via Heterogeneous Motif Graph Construction
Figure 2 for Molecular Graph Representation Learning via Heterogeneous Motif Graph Construction
Figure 3 for Molecular Graph Representation Learning via Heterogeneous Motif Graph Construction
Figure 4 for Molecular Graph Representation Learning via Heterogeneous Motif Graph Construction
Viaarxiv icon

MotifExplainer: a Motif-based Graph Neural Network Explainer

Add code
Feb 01, 2022
Viaarxiv icon