Haonan Yuan

Haonan Yuan

Auto-generated profile, based on publicly available information

Haonan Yuan

SKLCCSE, School of Computer Science and Engineering, Beihang University, Beijing, China

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
30 April 2023
Verified
Conference Paper
Open access
XFXingcheng Fu
Xingcheng Fu
YWYuecen Wei
Yuecen Wei
QSQingyun Sun
Qingyun Sun
HYHaonan Yuan
Haonan Yuan
Jia WUJia WU
Jia WU
JLJianxin Li
Jianxin Li
Learning unbiased node representations for imbalanced samples in the graph has become a more remarkable and important topic. For the graph, a significant challenge is that the topological properties of the nodes (e.g., locations, roles) are unbalanced (topology-imbalance), other than the number of training labeled nodes (quantity-imbalance). Existing studies on topology-imbalance focus on the location or the local neighborhood structure of nodes, ignoring the global underlying hierarchical properties of the graph, i.e., hierarchy. In the real-world scenario, the hierarchical structure of graph data reveals important topological properties of graphs and is relevant to a wide range of applications. We find that training labeled nodes with different hierarchical properties have a significant impact on the node classification tasks and confirm it in our experiments. It is well known that hyperbolic geometry has a unique advantage in representing the hierarchical structure of graphs. Therefore, we attempt to explore the hierarchy-imbalance issue for node classification of graph neural networks with a novelty perspective of hyperbolic geometry, including its characteristics and causes. Then, we propose a novel hyperbolic geometric hierarchy-imbalance learning framework, named HyperIMBA, to alleviate the hierarchy-imbalance issue caused by uneven hierarchy-levels and cross-hierarchy connectivity patterns of labeled nodes. Extensive experimental results demonstrate the superior effectiveness of HyperIMBA for hierarchy-imbalance node classification tasks.

13 May 2024
Verified
Conference Paper
Open access
HYHaonan Yuan
Haonan Yuan
QSQingyun Sun
Qingyun Sun
XFXingcheng Fu
Xingcheng Fu
Cheng JiCheng Ji
Cheng Ji
JLJianxin Li
Jianxin Li
Dynamic Graphs widely exist in the real world, which carry complicated spatial and temporal feature patterns, challenging their representation learning. Dynamic Graph Neural Networks (DGNNs) have shown impressive predictive abilities by exploiting the intrinsic dynamics. However, DGNNs exhibit limited robustness, prone to adversarial attacks. This paper presents the novelDynamic Graph Information Bottleneck (DGIB) framework to learn robust and discriminative representations. Leveraged by the Information Bottleneck (IB) principle, we first propose the expected optimal representations should satisfy theMinimal-Sufficient-Consensual (MSC) Condition. To compress redundant as well as conserve meritorious information into latent representation, DGIB iteratively directs and refines the structural and feature information flow passing through graph snapshots. To meet theMSC Condition, we decompose the overall IB objectives into DGIBMS and DGIBC, in which the DGIB_MS channel aims to learn the minimal and sufficient representations, with the DGIBC channel guarantees the predictive consensus. Extensive experiments on real-world and synthetic dynamic graph datasets demonstrate the superior robustness of DGIB against adversarial attacks compared with state-of-the-art baselines in the link prediction task. To the best of our knowledge, DGIB is the first work to learn robust representations of dynamic graphs grounded in the information-theoretic IB principle.



1 October 2026 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
QSQingyun Sun
Qingyun Sun
HYHaonan Yuan
Haonan Yuan
YHYi Huang
Yi Huang
ZZZiwei Zhang
Ziwei Zhang
XFXingcheng Fu
Xingcheng Fu
PYPhilip S. Yu
Philip S. Yu