Weigang Lu

Weigang Lu

Auto-generated profile, based on publicly available information

Weigang Lu

Department of Civil and Environmental Engineering, The Hong Kong University of Science and Technology, Hong Kong, Hong Kong

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 April 2024 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
WLWeigang Lu
Weigang Lu
YZYibing Zhan
Yibing Zhan
BLBinbin Lin
Binbin Lin
Ziyu GuanZiyu Guan
Ziyu Guan
LLLiu Liu
Liu Liu
DTDacheng Tao
Dacheng Tao
Graph Convolutional Networks (GCNs) suffer from performance degradation when models go deeper. However, earlier works only attributed the performance degeneration to over-smoothing. In this paper, we conduct theoretical and experimental analysis to explore the fundamental causes of performance degradation in deep GCNs: over-smoothing and gradient vanishing have a mutually reinforcing effect that causes the performance to deteriorate more quickly in deep GCNs. On the other hand, existing anti-over-smoothing methods all perform full convolutions up to the model depth. They could not well resist the exponential convergence of over-smoothing due to model depth increasing. In this work, we propose a simple yet effective plug-and-play module, SkipNode , to overcome the performance degradation of deep GCNs. It samples graph nodes in each convolutional layer to skip the convolution operation. In this way, both over-smoothing and gradient vanishing can be effectively suppressed since (1) not all nodes’features propagate through full layers and, (2) the gradient can be directly passed back through “skipped” nodes. We provide both theoretical analysis and empirical evaluation to demonstrate the efficacy of SkipNode and its superiority over SOTA baselines.

7 February 2022 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
YYYaming Yang
Yaming Yang
Ziyu GuanZiyu Guan
Ziyu Guan
WZWei Zhao
Wei Zhao
LWLu Weigang
Lu Weigang
BZBo Zong
Bo Zong
There has been a surge of researchers' interest in building predictive models over graphs. However, the overwhelming complexity of graph space often makes it challenging to extract interpretable and discriminative structural features for graph classification. In this work, we propose a new graph neural network model called Substructure Assembling Network (SAN) to learn graph representations for classification. The key innovation is a unified Substructure Assembling Unit (SAU), which is a variant of Recurrent Neural Network (RNN) designed to hierarchically assemble useful pieces of graph components so as to fabricate discriminative substructures. A key challenge is that SAUs need to process the neighbors of a node sequentially while no natural order is defined therein. SAN tries to make the model insensitive to neighborhood orders by randomly shuffling neighborhood sequences in training. However, this could suffer high variance, especially when the neighborhood size is large. Hence, we further propose to equip SAN with a novel module named Soft Sequence with Context Attention (SSCA). SAN-SSCA employs the proposed context attention technique to learn the best "soft" permutation of the neighbors w.r.t. classification. It helps the model achieve higher accuracy as well as lower variance. Experiments confirm the effectiveness of SAN-SSCA.

24 August 2024
Verified
Conference Paper
Open access
WLWeigang Lu
Weigang Lu
Ziyu GuanZiyu Guan
Ziyu Guan
WZWei Zhao
Wei Zhao
YYYaming Yang
Yaming Yang
Graph Neural Networks (GNNs) have revolutionized graph-based machine learning, but their heavy computational demands pose challenges for latency-sensitive edge devices in practical industrial applications. In response, a new wave of methods, collectively known as GNN-to-MLP Knowledge Distillation, has emerged. They aim to transfer GNN-learned knowledge to a more efficient MLP student, which offers faster, resource-efficient inference while maintaining competitive performance compared to GNNs. However, these methods face significant challenges in situations with insufficient training data and incomplete test data, limiting their applicability in real-world applications. To address these challenges, we propose AdaGMLP, an AdaBoosting GNN-to-MLP Knowledge Distillation framework. It leverages an ensemble of diverse MLP students trained on different subsets of labeled nodes, addressing the issue of insufficient training data. Additionally, it incorporates a Node Alignment technique for robust predictions on test data with missing or incomplete features. Our experiments on seven benchmark datasets with different settings demonstrate that AdaGMLP outperforms existing G2M methods, making it suitable for a wide range of latency-sensitive real-world applications. We have submitted our code to the GitHub repository (https://github.com/WeigangLu/AdaGMLP-KDD24).

16 January 2025 in Neurocomputing
Verified
Journal Article
Closed access
WLWeigang Lu
Weigang Lu
ZGZiyu Guan
Ziyu Guan
WZWei Zhao
Wei Zhao
YYYaming Yang
Yaming Yang
YLYuanhai Lv
Yuanhai Lv
DTDacheng Tao
Dacheng Tao


8 November 2025 in Pattern Recognition
Verified
Journal Article
Closed access
MYMeng Yan
Meng Yan
Cai XuCai Xu
Cai Xu
Ziyu GuanZiyu Guan
Ziyu Guan
WZWei Zhao
Wei Zhao
XWXujing Wang
Xujing Wang
WLWeigang Lu
Weigang Lu