Shaohua Fan

Shaohua Fan

Auto-generated profile, based on publicly available information

Shaohua Fan

Department of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
24 May 2022 in IEEE Transactions on Big Data
Verified
Journal Article
Closed access
Xiao WangXiao Wang
Xiao Wang
DBDeyu Bo
Deyu Bo
Chuan ShiChuan Shi
Chuan Shi
SFShaohua Fan
Shaohua Fan
YYYanfang Ye
Yanfang Ye
PYPhilip S. Yu
Philip S. Yu
Heterogeneous graphs (HGs) also known as heterogeneous information networks have become ubiquitous in real-world scenarios; therefore, HG embedding, which aim to learn representations in a lower-dimension space while preserving the heterogeneous structures and semantics for downstream tasks (e.g., node/graph classification, node clustering, link prediction), has drawn considerable attentions. In this survey, we perform a comprehensive review of the recent development on HG embedding methods and techniques. We first introduce the basic concepts of HG and discuss the unique challenges brought by the heterogeneity for HG embedding; and then we systemically survey and categorize the state-of-the-art HG embedding methods based on the information they used in the learning process. In particular, for each representative HG embedding method, we provide detailed introduction and further analyze its pros and cons; meanwhile, we explore the transformativeness and applicability of different types of HG embedding methods in the real-world industrial environments. We further present several widely deployed systems that have demonstrated the success of HG embedding techniques in resolving real-world application problems. To facilitate future research and applications in this area, we also summarize the open-source code, existing graph learning platforms and benchmark datasets. Finally, we explore the additional issues and challenges of HG embedding and forecast the future research directions in this field.

2 October 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
SFShaohua Fan
Shaohua Fan
Xiao WangXiao Wang
Xiao Wang
Chuan ShiChuan Shi
Chuan Shi
Peng CuiPeng Cui
Peng Cui
BWBai Wang
Bai Wang
Graph Neural Networks (GNNs) are proposed without considering the agnostic distribution shifts between training graphs and testing graphs, inducing the degeneration of the generalization ability of GNNs in Out-Of-Distribution (OOD) settings. The fundamental reason for such degeneration is that most GNNs are developed based on the I.I.D hypothesis. In such a setting, GNNs tend to exploit subtle statistical correlations existing in the training set for predictions, even though it is a spurious correlation. This learning mechanism inherits from the common characteristics of machine learning approaches. However, such spurious correlations may change in the wild testing environments, leading to the failure of GNNs. Therefore, eliminating the impact of spurious correlations is crucial for stable GNN models. To this end, in this paper, we argue that the spurious correlation exists among subgraph-level units and analyze the degeneration of GNN in causal view. Based on the causal view analysis, we propose a general causal representation framework for stable GNN, called StableGNN. The main idea of this framework is to extract high-level representations from raw graph data first and resort to the distinguishing ability of causal inference to help the model get rid of spurious correlations. Particularly, to extract meaningful high-level representations, we exploit a differentiable graph pooling layer to extract subgraph-based representations by an end-to-end manner. Furthermore, inspired by the confounder balancing techniques from causal inference, based on the learned high-level representations, we propose a causal variable distinguishing regularizer to correct the biased training distribution by learning a set of sample weights. Hence, GNNs would concentrate more on the true connection between discriminative substructures and labels. Extensive experiments are conducted on both synthetic datasets with various distribution shift degrees and eight real-world OOD graph datasets. The results well verify that the proposed model StableGNN not only outperforms the state-of-the-arts but also provides a flexible framework to enhance existing GNNs. In addition, the interpretability experiments validate that StableGNN could leverage causal structures for predictions.

1 February 2022 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
SFShaohua Fan
Shaohua Fan
Xiao WangXiao Wang
Xiao Wang
Chuan ShiChuan Shi
Chuan Shi
KKKun Kuang
Kun Kuang
NLNian Liu
Nian Liu
BWBai Wang
Bai Wang
Most existing graph neural networks (GNNs) are proposed without considering the selection bias in data, i.e., the inconsistent distribution between the training set with the test set. In reality, the test data are not even available during the training process, making selection bias agnostic. Training GNNs with biased selected nodes leads to significant parameter estimation bias and greatly impacts the generalization ability on test nodes. In this article, we first present an experimental investigation, which clearly shows that the selection bias drastically hinders the generalization ability of GNNs, and theoretically proves that the selection bias will cause the biased estimation on GNN parameters. Then to remove the bias in GNN estimation, we propose a novel debiased GNNs (DGNN) with a differentiated decorrelation regularizer. The differentiated decorrelation regularizer estimates a sample weight for each labeled node such that the spurious correlation of learned embeddings could be eliminated. We analyze the regularizer in causal view and it motivates us to differentiate the weights of the variables based on their contribution to the confounding bias. Then, these sample weights are used for reweighting GNNs to eliminate the estimation bias, and thus, help to improve the stability of prediction on unknown test nodes. Comprehensive experiments are conducted on several challenging graph datasets with two kinds of label selection biases. The results well verify that our proposed model outperforms the state-of-the-art methods and DGNN is a flexible framework to enhance existing GNNs.

13 May 2024
Verified
Conference Paper
Open access
YLYibo Li
Yibo Li
Xiao WangXiao Wang
Xiao Wang
YXYujie Xing
Yujie Xing
SFShaohua Fan
Shaohua Fan
RWRuijia Wang
Ruijia Wang
Chuan ShiChuan Shi
Chuan Shi
Graph neural networks (GNNs) have achieved remarkable performance on graph-structured data. However, GNNs may inherit prejudice from the training data and make discriminatory predictions based on sensitive attributes, such as gender and race. Recently, there has been an increasing interest in ensuring fairness on GNNs, but all of them are under the assumption that the training and testing data are under the same distribution, i.e., training data and testing data are from the same graph. Will graph fairness performance decrease under distribution shifts? How does distribution shifts affect graph fairness learning? All these open questions are largely unexplored from a theoretical perspective. To answer these questions, we first theoretically identify the factors that determine bias on a graph. Subsequently, we explore the factors influencing fairness on testing graphs, with a noteworthy factor being the representation distances of certain groups between the training and testing graph. Motivated by our theoretical analysis, we propose our framework FatraGNN. Specifically, to guarantee fairness performance on unknown testing graphs, we propose a graph generator to produce numerous graphs with significant bias and under different distributions. Then we minimize the representation distances for each certain group between the training graph and generated graphs. This empowers our model to achieve high classification and fairness performance even on generated graphs with significant bias, thereby effectively handling unknown testing graphs. Experiments on real-world and semi-synthetic datasets demonstrate the effectiveness of our model in terms of both accuracy and fairness.

1 November 2017
Verified
Conference Paper
Closed access
XGXin Gao
Xin Gao
SFShaohua Fan
Shaohua Fan
XLXinpeng Li
Xinpeng Li
ZGZiming Guo
Ziming Guo
HZHao Zhang
Hao Zhang
XDXinping Diao
Xinping Diao
Object classification is one of main problems in computer vision and lots of state-of-the-art machine learning methods have been proposed recently. Traditional classifier may have the drawback of low effectiveness for image representations. In this paper, an improved eXtreme Gradient Boosting (XGBoost) based on weighted column (feature) subsampling is proposed to classify image representations for object classification. The contributions of the paper are as follows. First, Convolutional Neural Networks (CNN) pre-trained on large-scale image database ILSVRC and fine-tuned on PASCAL VOC 2012 dataset is used to extract features from object images. Besides, we concatenate multiple layers of learned features to obtain more information of image contents for determining their categories. Second, due to the high dimensional of extracted features, feature redundancy will unavoidably be incurred, so a weighted column subsampling method is proposed to applied to XGBoost algorithm, in order to draw the features by the importance during growing each tree. Furthermore, our proposed method is general, which can be easily extended to other methods which need column subsampling, when the feature of data is high dimensional and redundant. Finally, we validate performance of proposed method on the PASCAL VOC 2007 dataset. Compared with four typical methods, the proposed method has superior average precision (AP) on 5 out of 20 classes, e.g. the AP of person class we obtained is 92.1, 1% higher than that of best method mentioned above.

23 June 2025 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
XLXuzeng Li
Xuzeng Li
Tao ZhangTao Zhang
Tao Zhang
JWJian Wang
Jian Wang
ZHZhen Han
Zhen Han
NWNan Wang
Nan Wang
DNDusit Niyato
Dusit Niyato
The vast number of devices and the complexity of requirements present significant challenges in ensuring the security of nonterrestrial Internet of Things (NT-IoT). Although existing studies have proposed methods to defend against data theft and network interference attacks, there is still a need for more in-depth research on detecting data-level attacks in NTNs. Moreover, the vast and diverse nature of network traffic presents significant challenges in traffic modeling and feature extraction. Hypergraph neural networks have gained considerable attention because of capabilities in data modeling and feature extraction. However, most existing hypergraph neural networks are tailored for specific applications and are not adaptable to the detection of malicious encrypted traffic. To address these challenges, we first propose a hypergraph neural network-based malicious encrypted traffic detection framework to enhance the resilience of NT-IoT, enabling attack detection across uncrewed aerial vehicles, base stations and satellites. Then, we introduce a multidimensional encrypted traffic hypergraph network (METHGN). METHGN models the encrypted traffic from network, connection and time dimensions using hypergraph and uses hypergraph convolution network to extracts and fuse features. We conducted comparative experiments on IoT and The Onion Router Network encrypted traffic datasets for different classification tasks. Extensive experiments demonstrate the effectiveness and superiority of our approach.