Search Results for author:
Found 12 papers, 7 papers with code
Towards Versatile Graph Learning Approach: from the Perspective of Large Language Models
This paper proposes a novel conceptual prototype for designing versatile graph learning methods with LLMs, with a particular focus on the "where" and "how" perspectives.
Unleashing the Power of Graph Learning through LLM-based Autonomous Agents
With these agents, those components are processed by decomposing and completing step by step, thereby generating a solution for the given data automatically, regardless of the learning task on node or graph.
Search to Capture Long-range Dependency with Stacking GNNs for Graph Classification
In recent years, Graph Neural Networks (GNNs) have been popular in the graph classification task.
Enhancing Intra-class Information Extraction for Heterophilous Graphs: One Neural Architecture Search Approach
Despite the success, we observe two aspects that can be further improved: (a) enhancing the ego feature information extraction from node itself which is more reliable in extracting the intra-class information; (b) designing node-wise GNNs can better adapt to the nodes with different homophily ratios.
Ranked #2 on
Node Classification
on Actor
Graph Property Prediction on Open Graph Benchmark: A Winning Solution by Graph Neural Architecture Search
Aiming at two molecular graph datasets and one protein association subgraph dataset in OGB graph classification task, we design a graph neural network framework for graph classification task by introducing PAS(Pooling Architecture Search).
Bridging the Gap of AutoGraph between Academia and Industry: Analysing AutoGraph Challenge at KDD Cup 2020
Researchers naturally adopt Automated Machine Learning on Graph Learning, aiming to reduce the human effort and achieve generally top-performing GNNs, but their methods focus more on the architecture search.
Designing the Topology of Graph Neural Networks: A Novel Feature Fusion Perspective
To enjoy the benefits while alleviating the corresponding deficiencies of these two manners, we learn to design the topology of GNNs in a novel feature fusion perspective which is dubbed F$^2$GNN.
Learn Layer-wise Connections in Graph Neural Networks
In recent years, Graph Neural Networks (GNNs) have shown superior performance on diverse applications on real-world datasets.
Pooling Architecture Search for Graph Classification
To address this problem, we propose to use neural architecture search (NAS) to search for adaptive pooling architectures for graph classification.
Efficient Graph Neural Architecture Search
To obtain state-of-the-art (SOAT) data-specific GNN architectures, researchers turn to the neural architecture search (NAS) methods.
Simplifying Architecture Search for Graph Neural Network
Recent years have witnessed the popularity of Graph Neural Networks (GNN) in various scenarios.
Automated Machine Learning: From Principles to Practices
Machine learning (ML) methods have been developing rapidly, but configuring and selecting proper methods to achieve a desired performance is increasingly difficult and tedious.
