Fu Lin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Fu Lin has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Xuexiong Luo
School of Computing, Macquarie University, Sydney, NSW, Australia
5 shared publications - Wenbin Hu
School of Computer Science, Wuhan University, Wuhan 430072, China
4 shared publications - Mingkang Li
School of Computer Science, Wuhan University, Wuhan, Hubei, China
3 shared publications - Jia Wu
Macquarie University
2 shared publications - Yaoyang Li
Wuhan University, Wuhan, Hubei, China
2 shared publications - Yue Zhang
Wuhan University
2 shared publications
Latest Publications
- 9 June 2026
- Published by Springer Nature
- p. 329-341
Graph Anomaly Detection Boundary Learning via Local and Global Structure Modeling
- 9 June 2026
- Published by Springer Nature
- p. 329-341
Graph Anomaly Detection Boundary Learning via Local and Global Structure Modeling
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 6540-6548
GTHNA: Local-global Graph Transformer with Memory Reconstruction for Holistic Node Anomaly Evaluation
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 6540-6548
Open AccessGTHNA: Local-global Graph Transformer with Memory Reconstruction for Holistic Node Anomaly Evaluation
- Open Access
GTHNA: Local-global Graph Transformer with Memory Reconstruction for Holistic Node Anomaly Evaluation
Anomaly detection in graph-structured data is an inherently challenging problem, as it requires the identification of rare nodes that deviate from the majority in both their structural and behavioral characteristics. Existing methods, such as those based on graph convolutional networks (GCNs), often suffer from over-smoothing, which causes the learned node representations to become indistinguishable. Furthermore, graph reconstruction-based approaches are vulnerable to anomalous node interference during the reconstruction process, leading to inaccurate anomaly detection. In this work, we propose a novel and holistic anomaly evaluation framework that integrates three key components: a local-global Transformer encoder, a memory-guided reconstruction mechanism, and a multi-scale representation matching strategy. These components work synergistically to enhance the model's ability to capture both local and global structural dependencies, suppress the influence of anomalous nodes, and assess anomalies from multiple levels of granularity. Anomaly scores are computed by combining reconstruction errors and memory matching signals, resulting in a more robust evaluation. Extensive experiments on seven benchmark datasets demonstrate that our method outperforms existing state-of-the-art approaches, offering a comprehensive and generalizable solution for anomaly detection across various graph domains.
Open AccessGTHNA: Local-global Graph Transformer with Memory Reconstruction for Holistic Node Anomaly Evaluation
Anomaly detection in graph-structured data is an inherently challenging problem, as it requires the identification of rare nodes that deviate from the majority in both their structural and behavioral characteristics. Existing methods, such as those based on graph convolutional networks (GCNs), often suffer from over-smoothing, which causes the learned node representations to become indistinguishable. Furthermore, graph reconstruction-based approaches are vulnerable to anomalous node interference during the reconstruction process, leading to inaccurate anomaly detection. In this work, we propose a novel and holistic anomaly evaluation framework that integrates three key components: a local-global Transformer encoder, a memory-guided reconstruction mechanism, and a multi-scale representation matching strategy. These components work synergistically to enhance the model's ability to capture both local and global structural dependencies, suppress the influence of anomalous nodes, and assess anomalies from multiple levels of granularity. Anomaly scores are computed by combining reconstruction errors and memory matching signals, resulting in a more robust evaluation. Extensive experiments on seven benchmark datasets demonstrate that our method outperforms existing state-of-the-art approaches, offering a comprehensive and generalizable solution for anomaly detection across various graph domains.
- 24 December 2024
- Published by Elsevier in Neural Networks
- Vol. 184, 107068
Unified Knowledge-Guided Molecular Graph Encoder with multimodal fusion and multi-task learning
- 24 December 2024
- Published by Elsevier in Neural Networks
- Vol. 184, 107068
Unified Knowledge-Guided Molecular Graph Encoder with multimodal fusion and multi-task learning
- 1 August 2024
- Published by Springer Nature
- p. 75-87
WARM: An Interpretability Module with Weighted Association Rule Mining for Recommendation Systems
- 1 August 2024
- Published by Springer Nature
- p. 75-87
WARM: An Interpretability Module with Weighted Association Rule Mining for Recommendation Systems
- Open Access
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Imbalanced Graph-Level Anomaly Detection via Counterfactual Augmentation and Feature Learning
Graph-level anomaly detection (GLAD) has already gained significant importance and has become a popular field of study, attracting considerable attention across numerous downstream works. The core focus of this domain is to capture and highlight the anomalous information within given graph datasets. In most existing studies, anomalies are often the instances of few. The stark imbalance misleads current GLAD methods to focus on learning the patterns of normal graphs more, further impacting anomaly detection performance. Moreover, existing methods predominantly utilize the inherent features of nodes to identify anomalous graph patterns which is approved suboptimal according to our experiments. In this work, we propose an imbalanced GLAD method via counterfactual augmentation and feature learning. Specifically, we first construct anomalous samples based on counterfactual learning, aiming to expand and balance the datasets. Additionally, we construct a module based on Graph Neural Networks (GNNs), which allows us to utilize degree attributes to complement the inherent attribute features of nodes. Then, we design an adaptive weight learning module to integrate features tailored to different datasets effectively to avoid indiscriminately treating all features as equivalent. Furthermore, extensive baseline experiments conducted on public datasets substantiate the robustness and effectiveness. Besides, we apply the model to brain disease datasets, which can prove the generalization capability of our work. The source code of our work is available online1.
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessImbalanced Graph-Level Anomaly Detection via Counterfactual Augmentation and Feature Learning
Graph-level anomaly detection (GLAD) has already gained significant importance and has become a popular field of study, attracting considerable attention across numerous downstream works. The core focus of this domain is to capture and highlight the anomalous information within given graph datasets. In most existing studies, anomalies are often the instances of few. The stark imbalance misleads current GLAD methods to focus on learning the patterns of normal graphs more, further impacting anomaly detection performance. Moreover, existing methods predominantly utilize the inherent features of nodes to identify anomalous graph patterns which is approved suboptimal according to our experiments. In this work, we propose an imbalanced GLAD method via counterfactual augmentation and feature learning. Specifically, we first construct anomalous samples based on counterfactual learning, aiming to expand and balance the datasets. Additionally, we construct a module based on Graph Neural Networks (GNNs), which allows us to utilize degree attributes to complement the inherent attribute features of nodes. Then, we design an adaptive weight learning module to integrate features tailored to different datasets effectively to avoid indiscriminately treating all features as equivalent. Furthermore, extensive baseline experiments conducted on public datasets substantiate the robustness and effectiveness. Besides, we apply the model to brain disease datasets, which can prove the generalization capability of our work. The source code of our work is available online1.
- 5 November 2023
- Published by Springer Nature
- p. 261-276
Discriminative Graph-Level Anomaly Detection via Dual-Students-Teacher Model
- 5 November 2023
- Published by Springer Nature
- p. 261-276
Discriminative Graph-Level Anomaly Detection via Dual-Students-Teacher Model
- Open Access
- 10 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Multi-representations Space Separation based Graph-level Anomaly-aware Detection
- 10 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessMulti-representations Space Separation based Graph-level Anomaly-aware Detection
- Open Access
Prompt-Learning for Cross-Lingual Relation Extraction
Relation Extraction (RE) is a crucial task in Information Extraction, which entails predicting relationships between entities within a given sentence. However, extending pre-trained RE models to other languages is challenging, particularly in real-world scenarios where Cross-Lingual Relation Extraction (XRE) is required. Despite recent advancements in Prompt-Learning, which involves transferring knowledge from Multilingual Pre-trained Language Models (PLMs) to diverse downstream tasks, there is limited research on the effective use of multilingual PLMs with prompts to improve XRE. In this paper, we present a novel XRE algorithm based on Prompt-Tuning, referred to as Prompt-XRE. To evaluate its effectiveness, we design and implement several prompt templates, including hard, soft, and hybrid prompts, and empirically test their performance on competitive multilingual PLMs, specifically mBART. Our extensive experiments, conducted on the low-resource ACE05 benchmark across multiple languages, demonstrate that our Prompt-XRE algorithm significantly outperforms both vanilla multilingual PLMs and other existing models, achieving state-of-the-art performance in XRE. To further show the generalization of our Prompt-XRE on larger data scales, we construct and release a new XRE dataset- WMT17-EnZh XRE, containing 0.9M English-Chinese pairs extracted from WMT 2017 parallel corpus. Experiments on WMT17-EnZh XRE also show the effectiveness of our Prompt-XRE against other competitive baselines. The code and newly constructed dataset are freely available at \url{https://github.com/HSU-CHIA-MING/Prompt-XRE}.
Open AccessPrompt-Learning for Cross-Lingual Relation Extraction
Relation Extraction (RE) is a crucial task in Information Extraction, which entails predicting relationships between entities within a given sentence. However, extending pre-trained RE models to other languages is challenging, particularly in real-world scenarios where Cross-Lingual Relation Extraction (XRE) is required. Despite recent advancements in Prompt-Learning, which involves transferring knowledge from Multilingual Pre-trained Language Models (PLMs) to diverse downstream tasks, there is limited research on the effective use of multilingual PLMs with prompts to improve XRE. In this paper, we present a novel XRE algorithm based on Prompt-Tuning, referred to as Prompt-XRE. To evaluate its effectiveness, we design and implement several prompt templates, including hard, soft, and hybrid prompts, and empirically test their performance on competitive multilingual PLMs, specifically mBART. Our extensive experiments, conducted on the low-resource ACE05 benchmark across multiple languages, demonstrate that our Prompt-XRE algorithm significantly outperforms both vanilla multilingual PLMs and other existing models, achieving state-of-the-art performance in XRE. To further show the generalization of our Prompt-XRE on larger data scales, we construct and release a new XRE dataset- WMT17-EnZh XRE, containing 0.9M English-Chinese pairs extracted from WMT 2017 parallel corpus. Experiments on WMT17-EnZh XRE also show the effectiveness of our Prompt-XRE against other competitive baselines. The code and newly constructed dataset are freely available at \url{https://github.com/HSU-CHIA-MING/Prompt-XRE}.
- 23 October 2017
- Published by Springer Nature in Wireless Networks
- Vol. 25 (2) , 861-874
OCSM: an optimized channel split method—towards real-time and on-demand data broadcast scheduling
- 23 October 2017
- Published by Springer Nature in Wireless Networks
- Vol. 25 (2) , 861-874
OCSM: an optimized channel split method—towards real-time and on-demand data broadcast scheduling