no code implementations • 18 Feb 2024 • Lanning Wei, Jun Gao, Huan Zhao, Quanming Yao
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.
no code implementations • 8 Sep 2023 • Lanning Wei, Zhiqiang He, Huan Zhao, Quanming Yao
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.
1 code implementation • 17 Feb 2023 • Lanning Wei, Zhiqiang He, Huan Zhao, Quanming Yao
In recent years, Graph Neural Networks (GNNs) have been popular in the graph classification task.
no code implementations • 20 Nov 2022 • Lanning Wei, Zhiqiang He, Huan Zhao, Quanming Yao
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
1 code implementation • 13 Jul 2022 • Xu Wang, Huan Zhao, Lanning Wei, Quanming Yao
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).
1 code implementation • 6 Apr 2022 • Zhen Xu, Lanning Wei, Huan Zhao, Rex Ying, Quanming Yao, Wei-Wei Tu, Isabelle Guyon
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.
2 code implementations • 29 Dec 2021 • Lanning Wei, Huan Zhao, Zhiqiang He
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.
no code implementations • 27 Dec 2021 • Lanning Wei, Huan Zhao, Zhiqiang He
In recent years, Graph Neural Networks (GNNs) have shown superior performance on diverse applications on real-world datasets.
3 code implementations • 24 Aug 2021 • Lanning Wei, Huan Zhao, Quanming Yao, Zhiqiang He
To address this problem, we propose to use neural architecture search (NAS) to search for adaptive pooling architectures for graph classification.
no code implementations • 1 Jan 2021 • Huan Zhao, Lanning Wei, Quanming Yao, Zhiqiang He
To obtain state-of-the-art (SOAT) data-specific GNN architectures, researchers turn to the neural architecture search (NAS) methods.
2 code implementations • 26 Aug 2020 • Huan Zhao, Lanning Wei, Quanming Yao
Recent years have witnessed the popularity of Graph Neural Networks (GNN) in various scenarios.
1 code implementation • 31 Oct 2018 • Zhenqian Shen, Yongqi Zhang, Lanning Wei, Huan Zhao, Quanming Yao
Machine learning (ML) methods have been developing rapidly, but configuring and selecting proper methods to achieve a desired performance is increasingly difficult and tedious.