Search Results for author:
Found 8 papers, 1 papers with code
Sculpting Molecules in 3D: A Flexible Substructure Aware Framework for Text-Oriented Molecular Optimization
This work not only holds general significance for the advancement of deep learning methodologies but also paves the way for a transformative shift in molecular design strategies.
A quatum inspired neural network for geometric modeling
By conceiving physical systems as 3D many-body point clouds, geometric graph neural networks (GNNs), such as SE(3)/E(3) equivalent GNNs, have showcased promising performance.
Molecule Joint Auto-Encoding: Trajectory Pretraining with 2D and 3D Diffusion
The fundamental building block for drug discovery is molecule geometry and thus, the molecule's geometrical representation is the main bottleneck to better utilize machine learning techniques for drug discovery.
NeutronStream: A Dynamic GNN Training Framework with Sliding Window for Graph Streams
Though many dynamic GNN models have emerged to learn from evolving graphs, the training process of these dynamic GNNs is dramatically different from traditional GNNs in that it captures both the spatial and temporal dependencies of graph updates.
Large Language Models as Topological Structure Enhancers for Text-Attributed Graphs
The latest advancements in large language models (LLMs) have revolutionized the field of natural language processing (NLP).
Empower Text-Attributed Graphs Learning with Large Language Models (LLMs)
In order to tackle this challenge, we propose a lightweight paradigm called ENG, which adopts a plug-and-play approach to empower text-attributed graphs through node generation using LLMs.
DiskANN++: Efficient Page-based Search over Isomorphic Mapped Graph Index using Query-sensitivity Entry Vertex
The main drawback of graph-based ANNS is that a graph index would be too large to fit into the memory especially for a large-scale $\mathcal{X}$.
CGCL: Collaborative Graph Contrastive Learning without Handcrafted Graph Data Augmentations
In this paper, we show the potential hazards of inappropriate augmentations and then propose a novel Collaborative Graph Contrastive Learning framework (CGCL).
