Yihong Luo

Yihong Luo

Auto-generated profile, based on publicly available information

Yihong Luo

The Hong Kong University of Science and Technology

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
1 August 2023
Verified
Conference Paper
Open access
PDF file
YCYuhan Chen
Yuhan Chen
YLYihong Luo
Yihong Luo
JTJing Tang
Jing Tang
LYLiang Yang
Liang Yang
SQSiya Qiu
Siya Qiu
XCXiaochun Cao
Xiaochun Cao
Heterophily has been considered as an issue that hurts the performance of Graph Neural Networks (GNNs). To address this issue, some existing work uses a graph-level weighted fusion of the information of multi-hop neighbors to include more nodes with homophily. However, the heterophily might differ among nodes, which requires to consider the local topology. Motivated by it, we propose to use the local similarity (LocalSim) to learn node-level weighted fusion, which can also serve as a plug-and-play module. For better fusion, we propose a novel and efficient Initial Residual Difference Connection (IRDC) to extract more informative multi-hop information. Moreover, we provide theoretical analysis on the effectiveness of LocalSim representing node homophily on synthetic graphs. Extensive evaluations over real benchmark datasets show that our proposed method, namely Local Similarity Graph Neural Network (LSGNN), can offer comparable or superior state-of-the-art performance on both homophilic and heterophilic graphs. Meanwhile, the plug-and-play model can significantly boost the performance of existing GNNs.

27 November 2024
Verified
Book Chapter
Closed access
PDF file
YLYihong Luo
Yihong Luo
SQSiya Qiu
Siya Qiu
XTXingjian Tao
Xingjian Tao
YCYujun Cai
Yujun Cai
JTJing Tang
Jing Tang

19 July 2026
Verified
Conference Paper
Open access
YSYifan Song
Yifan Song
FYFenglin Yu
Fenglin Yu
YLYihong Luo
Yihong Luo
XTXingjian Tao
Xingjian Tao
SQSiya Qiu
Siya Qiu
JTJing Tang
Jing Tang
Incomplete node features are ubiquitous in real-world scenarios such as user profiling and cold-start recommendation, which severely hinders the practical deployment of graph learning systems (e.g., GNNs). Existing solutions typically rely on diffusion-based structural smoothing (e.g., feature propagation) to impute missing values. However, we find that these approaches suffer from structural overfitting, leading to three progressive challenges: 1) performance degradation on disjoint graphs, 2) loss of semantic diversity due to over-smoothing, and 3) feature distribution shift when generalizing to unseen graph structures (inductive tasks). To address these challenges, we introduce the DART framework. It begins by employing Global Structural Augmentation (GSA), which establishes global correlations to bridge disjoint components and extend diffusion coverage. Building upon this, we design a semantic rectifier based on masked autoencoding. This module learns the latent feature manifold to recover natural semantic details. Crucially, we introduce a test-time distribution rectification mechanism that projects structurally biased features back onto the learned manifold during inference, effectively bridging the inductive distribution gap. Furthermore, considering that synthetic masking fails to reflect realworld sparsity, we present a new dataset Sailing collected from voyage records with naturally missing attributes. Extensive experiments on six public datasets and Sailing demonstrate that DART significantly outperforms state-of-the-art methods in both transductive and inductive settings. Our code and dataset are available at https://github.com/yfsong00/DART.

20 June 2023 in arXiv
Verified
Preprint
Open access
PDF file
YCYuhan Chen
Yuhan Chen
YLYihong Luo
Yihong Luo
JTJing Tang
Jing Tang
LYLiang Yang
Liang Yang
SQSiya Qiu
Siya Qiu
XCXiaochun Cao
Xiaochun Cao
Heterophily has been considered as an issue that hurts the performance of Graph Neural Networks (GNNs). To address this issue, some existing work uses a graph-level weighted fusion of the information of multi-hop neighbors to include more nodes with homophily. However, the heterophily might differ among nodes, which requires to consider the local topology. Motivated by it, we propose to use the local similarity (LocalSim) to learn node-level weighted fusion, which can also serve as a plug-and-play module. For better fusion, we propose a novel and efficient Initial Residual Difference Connection (IRDC) to extract more informative multi-hop information. Moreover, we provide theoretical analysis on the effectiveness of LocalSim representing node homophily on synthetic graphs. Extensive evaluations over real benchmark datasets show that our proposed method, namely Local Similarity Graph Neural Network (LSGNN), can offer comparable or superior state-of-the-art performance on both homophilic and heterophilic graphs. Meanwhile, the plug-and-play model can significantly boost the performance of existing GNNs. Our code is provided at https://github.com/draym28/LSGNN.

24 December 2024 in Ocean Engineering
Verified
Journal Article
Closed access
SQSiya Qiu
Siya Qiu
YLYihong Luo
Yihong Luo
QLQiong Luo
Qiong Luo
JTJing Tang
Jing Tang