Xiaoxiao Ma
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xiaoxiao Ma has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Jia Wu
Macquarie University
11 shared publications - Jian Yang
School of Computing, Macquarie University, Sydney, NSW, Australia
11 shared publications - Shan Xue
School of Computing, Macquarie University, Sydney, NSW, Australia
6 shared publications - Bingbing Xie
School of Information Management, Wuhan University, Wuhan, China
4 shared publications - Hao Fan
Wuhan University
4 shared publications - Quan Z. Sheng
Macquarie University
3 shared publications
Latest Publications
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1605-1616
Semi-Supervised Fake News Detection with Mixture of Experts
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1605-1616
Open AccessSemi-Supervised Fake News Detection with Mixture of Experts
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 901-912
Revisiting Graph-Level Anomaly Detection: From Partially to Fully Unsupervised Learning
Graph-level anomaly detection (GLAD) is a critical task to identify graphs with abnormal properties in various domains, ranging from fraudulent social networks to malicious botnets on online platforms. The dominant paradigm for existing GLAD detectors has been partially unsupervised, relying on training data composed exclusively of normal samples. However, this partially unsupervised paradigm inevitably requires a costly expert filtering process to ensure the training data is free of anomalies. This creates a significant gap between current approaches and the real-world necessity of a fully unsupervised paradigm, which involves training a model directly on real-world data ''as-is'', with its inherent mix of normal and anomalous samples. To bridge this gap, we incorporate uncertainty learning into GLAD to promote fully unsupervised learning. We propose two frameworks: Score Uncertainty Learning (SUL) and Graph-data Uncertainty Learning (GUL). Specifically, SUL enhances existing GLAD detectors by modeling uncertainty through Gaussian distributions over the detectors' predictions, adaptively attenuating the influence of potential anomalies. GUL is an end-to-end framework that iteratively optimizes anomaly detection and uncertainty modeling via an Expectation-Maximization algorithm. In addition, we develop a dedicated loss that utilizes potential anomalies to enhance the effectiveness and robustness of GUL. Empirical results on sixteen benchmark datasets, covering real-world graphs from social networks and online platforms, demonstrate the superiority of our methods and highlight the promise of incorporating uncertainty into fully unsupervised GLAD.
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 901-912
Open AccessRevisiting Graph-Level Anomaly Detection: From Partially to Fully Unsupervised Learning
Graph-level anomaly detection (GLAD) is a critical task to identify graphs with abnormal properties in various domains, ranging from fraudulent social networks to malicious botnets on online platforms. The dominant paradigm for existing GLAD detectors has been partially unsupervised, relying on training data composed exclusively of normal samples. However, this partially unsupervised paradigm inevitably requires a costly expert filtering process to ensure the training data is free of anomalies. This creates a significant gap between current approaches and the real-world necessity of a fully unsupervised paradigm, which involves training a model directly on real-world data ''as-is'', with its inherent mix of normal and anomalous samples. To bridge this gap, we incorporate uncertainty learning into GLAD to promote fully unsupervised learning. We propose two frameworks: Score Uncertainty Learning (SUL) and Graph-data Uncertainty Learning (GUL). Specifically, SUL enhances existing GLAD detectors by modeling uncertainty through Gaussian distributions over the detectors' predictions, adaptively attenuating the influence of potential anomalies. GUL is an end-to-end framework that iteratively optimizes anomaly detection and uncertainty modeling via an Expectation-Maximization algorithm. In addition, we develop a dedicated loss that utilizes potential anomalies to enhance the effectiveness and robustness of GUL. Empirical results on sixteen benchmark datasets, covering real-world graphs from social networks and online platforms, demonstrate the superiority of our methods and highlight the promise of incorporating uncertainty into fully unsupervised GLAD.
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 1505-1516
GD endrite: On Heterophilous Graph Contexts Mining with Versatile Neural Dendrites Framework
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 1505-1516
Open AccessGD endrite: On Heterophilous Graph Contexts Mining with Versatile Neural Dendrites Framework
- 6 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 12 (5) , 3948-3961
Contrastive Multi-Knowledge Graph Learning for Fake News Detection
The widespread dissemination of fake news on social media platforms has significantly disrupted people's daily lives, causing substantial inconvenience and loss. Although fake news detection has captivated great research effort, most of the existing works either overlook the complementary ground knowledge, formulated in individual knowledge graphs (KGs) or ignore multiple aspects of knowledge in different knowledge graphs. In this paper, we propose a novel contrastive learning framework for investigating the complementary knowledge in different knowledge graphs, which achieves superior fake news detection performance. We first model three components within news articles (i.e., news content, entities, and topics) as a heterogeneous graph (HG). Subsequently, we leverage the valuable factual evidence among real-world entities, which is enclosed in two open-source knowledge graphs (Wikidata and DBpedia), and augment the heterogeneous graph into three augmented graphs. We then fuse knowledge-enhanced high-level news representations from each augmented graph and extract a unified news representation through our proposed contrastive multi-knowledge graph learning framework, which is ultimately utilized to identify fake news. We conduct extensive experiments on four public fake news datasets and demonstrate the superiority of our method over nine state-of-the-art baselines regarding five widely-used evaluation metrics (i.e., accuracy, precision, recall, F1-score, and ROC).
- 6 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 12 (5) , 3948-3961
Contrastive Multi-Knowledge Graph Learning for Fake News Detection
The widespread dissemination of fake news on social media platforms has significantly disrupted people's daily lives, causing substantial inconvenience and loss. Although fake news detection has captivated great research effort, most of the existing works either overlook the complementary ground knowledge, formulated in individual knowledge graphs (KGs) or ignore multiple aspects of knowledge in different knowledge graphs. In this paper, we propose a novel contrastive learning framework for investigating the complementary knowledge in different knowledge graphs, which achieves superior fake news detection performance. We first model three components within news articles (i.e., news content, entities, and topics) as a heterogeneous graph (HG). Subsequently, we leverage the valuable factual evidence among real-world entities, which is enclosed in two open-source knowledge graphs (Wikidata and DBpedia), and augment the heterogeneous graph into three augmented graphs. We then fuse knowledge-enhanced high-level news representations from each augmented graph and extract a unified news representation through our proposed contrastive multi-knowledge graph learning framework, which is ultimately utilized to identify fake news. We conduct extensive experiments on four public fake news datasets and demonstrate the superiority of our method over nine state-of-the-art baselines regarding five widely-used evaluation metrics (i.e., accuracy, precision, recall, F1-score, and ROC).
- Top Cited PapersOpen Access
- 22 March 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Recommender Systems
- Vol. 3 (3) , 1-22
Heterogeneous Hypergraph Neural Network for Social Recommendation using Attention Network
Graph neural networks (GNNs) have been used extensively as a backbone for social recommendation. However, their application to a diverse range of situations is still rather limited. This is because graph structures only leverage pairwise user relationships. They cannot capture the higher-order relationships so common in the real world, and ignoring the interest friends and strangers might have in similar items is severely hampering the expressiveness of the current graph-based recommendation models. Hence, in this article, we outline a heterogeneous hypergraph neural network for social recommendation, called Heterogeneous Hypergraph neural network for Social Recommendation using an Attention Network (HHGSA), that incorporates an attention network to address these issues. The hypergraph is able to represent higher-order relationships through five motifs: friend and stranger item appeal, item similarity, user similarity based on interactions with items, and social relations. Two modules, the attentive vertex aggregation module and the attentive hyperedge aggregation module, capture user and item attention. In addition, it has been discovered that similar items have identical appeal when displayed to users. A GNN aggregates the user embedding data, including information about the friend and stranger and item embeddings. Finally, information about users and items is aggregated for social recommendations. Extensive experiments on four datasets demonstrate that the HHGSA model outperforms a wide range of baselines and can significantly improve the accuracy of recommendations.
- 22 March 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Recommender Systems
- Vol. 3 (3) , 1-22
Top Cited PapersOpen AccessHeterogeneous Hypergraph Neural Network for Social Recommendation using Attention Network
Graph neural networks (GNNs) have been used extensively as a backbone for social recommendation. However, their application to a diverse range of situations is still rather limited. This is because graph structures only leverage pairwise user relationships. They cannot capture the higher-order relationships so common in the real world, and ignoring the interest friends and strangers might have in similar items is severely hampering the expressiveness of the current graph-based recommendation models. Hence, in this article, we outline a heterogeneous hypergraph neural network for social recommendation, called Heterogeneous Hypergraph neural network for Social Recommendation using an Attention Network (HHGSA), that incorporates an attention network to address these issues. The hypergraph is able to represent higher-order relationships through five motifs: friend and stranger item appeal, item similarity, user similarity based on interactions with items, and social relations. Two modules, the attentive vertex aggregation module and the attentive hyperedge aggregation module, capture user and item attention. In addition, it has been discovered that similar items have identical appeal when displayed to users. A GNN aggregates the user embedding data, including information about the friend and stranger and item embeddings. Finally, information about users and items is aggregated for social recommendations. Extensive experiments on four datasets demonstrate that the HHGSA model outperforms a wide range of baselines and can significantly improve the accuracy of recommendations.
- 18 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 37 (2) , 881-895
Rethinking Unsupervised Graph Anomaly Detection With Deep Learning: Residuals and Objectives
Anomalies often occur in real-world information networks/graphs, such as malevolent users in online review networks and fake news in social media. When representing such structured network data as graphs, anomalies usually appear as anomalous nodes that exhibit significantly deviated structure patterns, or different attributes, or the both. To date, numerous unsupervised methods have been developed to detect anomalies based on residual analysis, which assumes that anomalies will introduce larger residual errors (i.e., graph reconstruction loss). While these existing works achieved encouraging performance, in this paper, we formally prove that their employed learning objectives, i.e., MSE and cross-entropy losses, encounter significant limitations in learning the major data distributions, particularly for anomaly detection, and through our preliminary study, we reveal that the vanilla residual analysis-based methods cannot effectively investigate the rich graph structure. Upon these discoveries, we propose a novel structure-biased graph anomaly detection framework (SALAD) to attain anomalies’ divergent patterns with the assistance of a specially designed node representation augmentation approach. We further present two effective training objectives to empower SALAD to effectively capture the major structure and attribute distributions by emphasizing less on anomalies that introduce higher reconstruction errors under the encoder-decoder framework. The detection performance on eight widely-used datasets demonstrates SALAD's superiority over twelve state-of-the-art baselines. Additional ablation and case studies validate that our data augmentation method and training objectives result in the impressive performance.
- 18 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 37 (2) , 881-895
Rethinking Unsupervised Graph Anomaly Detection With Deep Learning: Residuals and Objectives
Anomalies often occur in real-world information networks/graphs, such as malevolent users in online review networks and fake news in social media. When representing such structured network data as graphs, anomalies usually appear as anomalous nodes that exhibit significantly deviated structure patterns, or different attributes, or the both. To date, numerous unsupervised methods have been developed to detect anomalies based on residual analysis, which assumes that anomalies will introduce larger residual errors (i.e., graph reconstruction loss). While these existing works achieved encouraging performance, in this paper, we formally prove that their employed learning objectives, i.e., MSE and cross-entropy losses, encounter significant limitations in learning the major data distributions, particularly for anomaly detection, and through our preliminary study, we reveal that the vanilla residual analysis-based methods cannot effectively investigate the rich graph structure. Upon these discoveries, we propose a novel structure-biased graph anomaly detection framework (SALAD) to attain anomalies’ divergent patterns with the assistance of a specially designed node representation augmentation approach. We further present two effective training objectives to empower SALAD to effectively capture the major structure and attribute distributions by emphasizing less on anomalies that introduce higher reconstruction errors under the encoder-decoder framework. The detection performance on eight widely-used datasets demonstrates SALAD's superiority over twelve state-of-the-art baselines. Additional ablation and case studies validate that our data augmentation method and training objectives result in the impressive performance.
- 13 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 12 (2) , 682-694
Multiknowledge and LLM-Inspired Heterogeneous Graph Neural Network for Fake News Detection
The widespread diffusion of fake news has become a critical problem on dynamic social media worldwide, which requires effective strategies for fake news detection to alleviate its hazardous consequences for society. However, most recent efforts only focus on the features of news content and social context without realizing the benefits of large language models (LLMs) and multiple knowledge graphs (KGs), thus failing to improve detection capabilities further. To tackle this issue, we present a multiknowledge and LLM-inspired heterogeneous graph neural network for fake news detection (MiLk-FD), by combining KGs, LLMs, and graph neural networks (GNNs). Specifically, we first model news content as a heterogeneous graph (HG) containing news, entity, and topic nodes and then fuse the knowledge from three KGs to augment the factual basis of news articles. Meanwhile, we leverage TransE to initialize the knowledge features and employ LLaMa2-7B to obtain the initial feature vectors of news articles. After that, we utilize the devised HG transformer to learn news embeddings with specific feature distribution in high-dimensional spaces by aggregating neighborhood information according to metapaths. Finally, a classifier based on multilayer perceptron (MLP) is trained to predict each news article as fake or true. Through experiments, we demonstrate that our proposed framework surpasses ten baselines according to accuracy, precision, F1-score, recall, and ROC in four public real-world benchmarks (i.e., COVID-19, FakeNewsNet, PAN2020, Liar).
- 13 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 12 (2) , 682-694
Multiknowledge and LLM-Inspired Heterogeneous Graph Neural Network for Fake News Detection
The widespread diffusion of fake news has become a critical problem on dynamic social media worldwide, which requires effective strategies for fake news detection to alleviate its hazardous consequences for society. However, most recent efforts only focus on the features of news content and social context without realizing the benefits of large language models (LLMs) and multiple knowledge graphs (KGs), thus failing to improve detection capabilities further. To tackle this issue, we present a multiknowledge and LLM-inspired heterogeneous graph neural network for fake news detection (MiLk-FD), by combining KGs, LLMs, and graph neural networks (GNNs). Specifically, we first model news content as a heterogeneous graph (HG) containing news, entity, and topic nodes and then fuse the knowledge from three KGs to augment the factual basis of news articles. Meanwhile, we leverage TransE to initialize the knowledge features and employ LLaMa2-7B to obtain the initial feature vectors of news articles. After that, we utilize the devised HG transformer to learn news embeddings with specific feature distribution in high-dimensional spaces by aggregating neighborhood information according to metapaths. Finally, a classifier based on multilayer perceptron (MLP) is trained to predict each news article as fake or true. Through experiments, we demonstrate that our proposed framework surpasses ten baselines according to accuracy, precision, F1-score, recall, and ROC in four public real-world benchmarks (i.e., COVID-19, FakeNewsNet, PAN2020, Liar).
- Open Access
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 2153-2164
Graph Anomaly Detection with Few Labels: A Data-Centric Approach
Anomalous node detection in a static graph faces significant challenges due to the rarity of anomalies and the substantial cost of labeling their deviant structure and attribute patterns. These challenges give rise to data-centric problems, including extremely imbalanced data distributions and intricate graph learning, which significantly impede machine learning and deep learning methods from discerning the patterns of graph anomalies with few labels. While these issues remain crucial, much of the current research focuses on addressing the induced technical challenges, treating the shortage of labeled data as a given. Distinct from previous efforts, this work focuses on tackling the data-centric problems by generating auxiliary training nodes that conform to the original graph topology and attribute distribution. We categorize this approach as data-centric, aiming to enhance existing anomaly detectors by training them on our synthetic data. However, the methods for generating nodes and the effectiveness of utilizing synthetic data for graph anomaly detection remain unexplored in the realm. To answer these questions, we thoroughly investigate the denoising diffusion model. Drawing from our observations on the diffusion process, we illuminate the shifts in graph energy distribution and establish two principles for designing denoising neural networks tailored to graph anomaly generation. From the insights, we propose a diffusion-based graph generation method to synthesize training nodes, which can be promptly integrated to work with existing anomaly detectors. The empirical results on eight widely-used datasets demonstrate our generated data can effectively enhance the nine state-of-the-art graph detectors' performance.
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 2153-2164
Open AccessGraph Anomaly Detection with Few Labels: A Data-Centric Approach
Anomalous node detection in a static graph faces significant challenges due to the rarity of anomalies and the substantial cost of labeling their deviant structure and attribute patterns. These challenges give rise to data-centric problems, including extremely imbalanced data distributions and intricate graph learning, which significantly impede machine learning and deep learning methods from discerning the patterns of graph anomalies with few labels. While these issues remain crucial, much of the current research focuses on addressing the induced technical challenges, treating the shortage of labeled data as a given. Distinct from previous efforts, this work focuses on tackling the data-centric problems by generating auxiliary training nodes that conform to the original graph topology and attribute distribution. We categorize this approach as data-centric, aiming to enhance existing anomaly detectors by training them on our synthetic data. However, the methods for generating nodes and the effectiveness of utilizing synthetic data for graph anomaly detection remain unexplored in the realm. To answer these questions, we thoroughly investigate the denoising diffusion model. Drawing from our observations on the diffusion process, we illuminate the shifts in graph energy distribution and establish two principles for designing denoising neural networks tailored to graph anomaly generation. From the insights, we propose a diffusion-based graph generation method to synthesize training nodes, which can be promptly integrated to work with existing anomaly detectors. The empirical results on eight widely-used datasets demonstrate our generated data can effectively enhance the nine state-of-the-art graph detectors' performance.
- Open Access
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 574-584
Divide and Denoise: Empowering Simple Models for Robust Semi-Supervised Node Classification against Label Noise
Graph neural networks (GNNs) based on message passing have achieved remarkable performance in graph machine learning. By combining it with the power of pseudo labeling, one can further push forward the performance on the task of semi-supervised node classification. However, most existing works assume that the training node labels are purely noise-free, while this strong assumption usually does not hold in practice. GNNs will overfit the noisy training labels and the adverse effects of mislabeled nodes can be exaggerated by being propagated to the remaining nodes through the graph structure, exacerbating the model failure. Worse still, the noisy pseudo labels could also largely undermine the model's reliability without special treatment. In this paper, we revisit the role of (1) message passing and (2) pseudo labels in the studied problem and try to address two denoising subproblems from the model architecture and algorithm perspective, respectively. Specifically, we first develop a label-noise robust GNN that discards the coupled message-passing scheme. Despite its simple architecture, this learning backbone prevents overfitting to noisy labels and also inherently avoids the noise propagation issue. Moreover, we propose a novel reliable graph pseudo labeling algorithm that can effectively leverage the knowledge of unlabeled nodes while mitigating the adverse effects of noisy pseudo labels. Based on those novel designs, we can attain exceptional effectiveness and efficiency in solving the studied problem. We conduct extensive experiments on benchmark datasets for semi-supervised node classification with different levels of label noise and show new state-of-the-art performance. The code is available at https://github.com/DND-NET/DND-NET.
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 574-584
Open AccessDivide and Denoise: Empowering Simple Models for Robust Semi-Supervised Node Classification against Label Noise
Graph neural networks (GNNs) based on message passing have achieved remarkable performance in graph machine learning. By combining it with the power of pseudo labeling, one can further push forward the performance on the task of semi-supervised node classification. However, most existing works assume that the training node labels are purely noise-free, while this strong assumption usually does not hold in practice. GNNs will overfit the noisy training labels and the adverse effects of mislabeled nodes can be exaggerated by being propagated to the remaining nodes through the graph structure, exacerbating the model failure. Worse still, the noisy pseudo labels could also largely undermine the model's reliability without special treatment. In this paper, we revisit the role of (1) message passing and (2) pseudo labels in the studied problem and try to address two denoising subproblems from the model architecture and algorithm perspective, respectively. Specifically, we first develop a label-noise robust GNN that discards the coupled message-passing scheme. Despite its simple architecture, this learning backbone prevents overfitting to noisy labels and also inherently avoids the noise propagation issue. Moreover, we propose a novel reliable graph pseudo labeling algorithm that can effectively leverage the knowledge of unlabeled nodes while mitigating the adverse effects of noisy pseudo labels. Based on those novel designs, we can attain exceptional effectiveness and efficiency in solving the studied problem. We conduct extensive experiments on benchmark datasets for semi-supervised node classification with different levels of label noise and show new state-of-the-art performance. The code is available at https://github.com/DND-NET/DND-NET.
- Open Access
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1272-1282
Heterogeneous Subgraph Transformer for Fake News Detection
Fake news is pervasive on social media, inflicting substantial harm on public discourse and societal well-being. We investigate the explicit structural information and textual features of news pieces by constructing a heterogeneous graph concerning the relations among news topics, entities, and content. Through our study, we reveal that fake news can be effectively detected in terms of the atypical heterogeneous subgraphs centered on them, which encapsulate the essential semantics and intricate relations between news elements. However, suffering from the heterogeneity, exploring such heterogeneous subgraphs remains an open problem. To bridge the gap, this work proposes a heterogeneous subgraph transformer HeteroSGT to exploit subgraphs in our constructed heterogeneous graph. In HeteroSGT, we first employ a pre-trained language model to derive both word-level and sentence-level semantics. Then the random walk with restart (RWR) is applied to extract subgraphs centered on each news, which are further fed to our proposed subgraph Transformer to quantify the authenticity. Extensive experiments on five real-world datasets demonstrate the superior performance of HeteroSGT over five baselines. Further case and ablation studies validate our motivation and demonstrate that performance improvement stems from our specially designed components.
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1272-1282
Open AccessHeterogeneous Subgraph Transformer for Fake News Detection
Fake news is pervasive on social media, inflicting substantial harm on public discourse and societal well-being. We investigate the explicit structural information and textual features of news pieces by constructing a heterogeneous graph concerning the relations among news topics, entities, and content. Through our study, we reveal that fake news can be effectively detected in terms of the atypical heterogeneous subgraphs centered on them, which encapsulate the essential semantics and intricate relations between news elements. However, suffering from the heterogeneity, exploring such heterogeneous subgraphs remains an open problem. To bridge the gap, this work proposes a heterogeneous subgraph transformer HeteroSGT to exploit subgraphs in our constructed heterogeneous graph. In HeteroSGT, we first employ a pre-trained language model to derive both word-level and sentence-level semantics. Then the random walk with restart (RWR) is applied to extract subgraphs centered on each news, which are further fed to our proposed subgraph Transformer to quantify the authenticity. Extensive experiments on five real-world datasets demonstrate the superior performance of HeteroSGT over five baselines. Further case and ablation studies validate our motivation and demonstrate that performance improvement stems from our specially designed components.