Can Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Can Wang has a total of 215 co-authors. Here are the top co-authors by number of shared publications:
Chi-Hung Chi
CSIRO
11 shared publications- Longbing Cao
Macquarie University, Sydney, NSW, Australia
11 shared publications - Weimin Li
School of Computer Engineering and Science, Shanghai University, Shanghai, P. R. China
7 shared publications - Yonghong Yu
College of Tongda, Nanjing University of Posts and Telecommunications, Nanjing, China
6 shared publications Yunwei Zhao
CNCERT/CC
6 shared publications- Shirui Pan
Griffith University, Australia
5 shared publications
Latest Publications
- 10 August 2026
- Published by Elsevier in Information Sciences
- Vol. 758
DSSG: Decoupled structural synergy for cross-view generative heterogeneous graph representation learning
- 10 August 2026
- Published by Elsevier in Information Sciences
- Vol. 758
DSSG: Decoupled structural synergy for cross-view generative heterogeneous graph representation learning
- 3 March 2026
- Published by Springer Nature in Applied Intelligence
- Vol. 56 (5) , 121
Adaptive triple collaborative learning for contrastive community discovery in heterogeneous graphs with fuzzy boundaries
- 3 March 2026
- Published by Springer Nature in Applied Intelligence
- Vol. 56 (5) , 121
Adaptive triple collaborative learning for contrastive community discovery in heterogeneous graphs with fuzzy boundaries
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 5822-5830
OASIS: Harnessing Diffusion Adversarial Network for Ocean Salinity Imputation using Sparse Drifter Trajectories
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 5822-5830
Open AccessOASIS: Harnessing Diffusion Adversarial Network for Ocean Salinity Imputation using Sparse Drifter Trajectories
- Open Access
Test-time GNN Model Evaluation on Dynamic Graphs
Dynamic graph neural networks (DGNNs) have emerged as a leading paradigm for learning from dynamic graphs, which are commonly used to model real-world systems and applications. However, due to the evolving nature of dynamic graph data distributions over time, well-trained DGNNs often face significant performance uncertainty when inferring on unseen and unlabeled test graphs in practical deployment. In this case, evaluating the performance of deployed DGNNs at test time is crucial to determine whether a well-trained DGNN is suited for inference on an unseen dynamic test graph. In this work, we introduce a new research problem: DGNN model evaluation, which aims to assess the performance of a specific DGNN model trained on observed dynamic graphs by estimating its performance on unseen dynamic graphs during test time. Specifically, we propose a Dynamic Graph neural network Evaluator, dubbed DyGEval, to address this new problem. The proposed DyGEval involves a two-stage framework: (1) test-time dynamic graph simulation, which captures the training-test distributional differences as supervision signals and trains an evaluator; and (2) DyGEval development and training, which accurately estimates the performance of the well-trained DGNN model on the test-time dynamic graphs. Extensive experiments demonstrate that the proposed DyGEval serves as an effective evaluator for assessing various DGNN backbones across different dynamic graphs under distribution shifts.
Open AccessTest-time GNN Model Evaluation on Dynamic Graphs
Dynamic graph neural networks (DGNNs) have emerged as a leading paradigm for learning from dynamic graphs, which are commonly used to model real-world systems and applications. However, due to the evolving nature of dynamic graph data distributions over time, well-trained DGNNs often face significant performance uncertainty when inferring on unseen and unlabeled test graphs in practical deployment. In this case, evaluating the performance of deployed DGNNs at test time is crucial to determine whether a well-trained DGNN is suited for inference on an unseen dynamic test graph. In this work, we introduce a new research problem: DGNN model evaluation, which aims to assess the performance of a specific DGNN model trained on observed dynamic graphs by estimating its performance on unseen dynamic graphs during test time. Specifically, we propose a Dynamic Graph neural network Evaluator, dubbed DyGEval, to address this new problem. The proposed DyGEval involves a two-stage framework: (1) test-time dynamic graph simulation, which captures the training-test distributional differences as supervision signals and trains an evaluator; and (2) DyGEval development and training, which accurately estimates the performance of the well-trained DGNN model on the test-time dynamic graphs. Extensive experiments demonstrate that the proposed DyGEval serves as an effective evaluator for assessing various DGNN backbones across different dynamic graphs under distribution shifts.
- Open Access
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 9, 7437-7445
M^2LLM: Multi-view Molecular Representation Learning with Large Language Models
Accurate molecular property prediction is a critical challenge with wide-ranging applications in chemistry, materials science, and drug discovery. Molecular representation methods, including fingerprints and graph neural networks (GNNs), achieve state-of-the-art results by effectively deriving features from molecular structures. However, these methods often overlook decades of accumulated semantic and contextual knowledge. Recent advancements in large language models (LLMs) demonstrate remarkable reasoning abilities and prior knowledge across scientific domains, leading us to hypothesize that LLMs can generate rich molecular representations when guided to reason in multiple perspectives. To address these gaps, we propose M^2LLM, a multi-view framework that integrates three perspectives: the molecular structure view, the molecular task view, and the molecular rules view. These views are fused dynamically to adapt to task requirements, and experiments demonstrate that M^2LLM achieves state-of-the-art performance on multiple benchmarks across classification and regression tasks. Moreover, we demonstrate that representation derived from LLM achieves exceptional performance by leveraging two core functionalities: the generation of molecular embeddings through their encoding capabilities and the curation of molecular features through advanced reasoning processes.
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 9, 7437-7445
Open AccessM^2LLM: Multi-view Molecular Representation Learning with Large Language Models
Accurate molecular property prediction is a critical challenge with wide-ranging applications in chemistry, materials science, and drug discovery. Molecular representation methods, including fingerprints and graph neural networks (GNNs), achieve state-of-the-art results by effectively deriving features from molecular structures. However, these methods often overlook decades of accumulated semantic and contextual knowledge. Recent advancements in large language models (LLMs) demonstrate remarkable reasoning abilities and prior knowledge across scientific domains, leading us to hypothesize that LLMs can generate rich molecular representations when guided to reason in multiple perspectives. To address these gaps, we propose M^2LLM, a multi-view framework that integrates three perspectives: the molecular structure view, the molecular task view, and the molecular rules view. These views are fused dynamically to adapt to task requirements, and experiments demonstrate that M^2LLM achieves state-of-the-art performance on multiple benchmarks across classification and regression tasks. Moreover, we demonstrate that representation derived from LLM achieves exceptional performance by leveraging two core functionalities: the generation of molecular embeddings through their encoding capabilities and the curation of molecular features through advanced reasoning processes.
- 19 August 2025
- Published by Springer Nature
- p. 349-355
Local-Aware Convolutional Modulation for Short-Term Sequential Recommendation
- 19 August 2025
- Published by Springer Nature
- p. 349-355
Local-Aware Convolutional Modulation for Short-Term Sequential Recommendation
- 19 August 2025
- Published by Springer Nature
- p. 126-141
Cross-Modal Sequential Point-of-Interest Recommendation with Lightweight Hybrid Fusion Strategy
- 19 August 2025
- Published by Springer Nature
- p. 126-141
Cross-Modal Sequential Point-of-Interest Recommendation with Lightweight Hybrid Fusion Strategy
- Open Access
$\text{M}^{2}$LLM: Multi-view Molecular Representation Learning with Large Language Models
Accurate molecular property prediction is a critical challenge with wide-ranging applications in chemistry, materials science, and drug discovery. Molecular representation methods, including fingerprints and graph neural networks (GNNs), achieve state-of-the-art results by effectively deriving features from molecular structures. However, these methods often overlook decades of accumulated semantic and contextual knowledge. Recent advancements in large language models (LLMs) demonstrate remarkable reasoning abilities and prior knowledge across scientific domains, leading us to hypothesize that LLMs can generate rich molecular representations when guided to reason in multiple perspectives. To address these gaps, we propose $\text{M}^{2}$LLM, a multi-view framework that integrates three perspectives: the molecular structure view, the molecular task view, and the molecular rules view. These views are fused dynamically to adapt to task requirements, and experiments demonstrate that $\text{M}^{2}$LLM achieves state-of-the-art performance on multiple benchmarks across classification and regression tasks. Moreover, we demonstrate that representation derived from LLM achieves exceptional performance by leveraging two core functionalities: the generation of molecular embeddings through their encoding capabilities and the curation of molecular features through advanced reasoning processes.
Open Access$\text{M}^{2}$LLM: Multi-view Molecular Representation Learning with Large Language Models
Accurate molecular property prediction is a critical challenge with wide-ranging applications in chemistry, materials science, and drug discovery. Molecular representation methods, including fingerprints and graph neural networks (GNNs), achieve state-of-the-art results by effectively deriving features from molecular structures. However, these methods often overlook decades of accumulated semantic and contextual knowledge. Recent advancements in large language models (LLMs) demonstrate remarkable reasoning abilities and prior knowledge across scientific domains, leading us to hypothesize that LLMs can generate rich molecular representations when guided to reason in multiple perspectives. To address these gaps, we propose $\text{M}^{2}$LLM, a multi-view framework that integrates three perspectives: the molecular structure view, the molecular task view, and the molecular rules view. These views are fused dynamically to adapt to task requirements, and experiments demonstrate that $\text{M}^{2}$LLM achieves state-of-the-art performance on multiple benchmarks across classification and regression tasks. Moreover, we demonstrate that representation derived from LLM achieves exceptional performance by leveraging two core functionalities: the generation of molecular embeddings through their encoding capabilities and the curation of molecular features through advanced reasoning processes.
- 12 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Intelligent Systems
- Vol. 40 (3) , 5-9
Point-of-Interest Recommendations and Large Language Models: A Powerful Combination
Point-of-interest (POI) recommendation systems have become a cornerstone of personalized user experiences in various applications, such as navigation, tourism, and retail. Recent advancements in artificial intelligence, particularly the integration of large language models (LLMs), have opened new possibilities for building a more powerful and comprehensive POI recommendation system. This work first reviews the latest research outcomes that leverage LLMs for POI recommendation, highlighting their contribution to dealing with the long-standing challenges of POI recommendation systems. Furthermore, we identify untapped potentials of LLM-based POI recommenders across the recommendation pipeline, encompassing multimodal feature augmentation, unified encoding, hybrid task learning for scoring and ranking, and dynamic user interaction. By exploring these opportunities, future research can transform POI recommendation systems into adaptive, user-centric assistants, delivering seamless, scalable, and personalized experiences. This article aims to provide a comprehensive overview of recent advancements and propose future directions for leveraging LLMs to redefine the next generation of POI recommendation systems.
- 12 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Intelligent Systems
- Vol. 40 (3) , 5-9
Point-of-Interest Recommendations and Large Language Models: A Powerful Combination
Point-of-interest (POI) recommendation systems have become a cornerstone of personalized user experiences in various applications, such as navigation, tourism, and retail. Recent advancements in artificial intelligence, particularly the integration of large language models (LLMs), have opened new possibilities for building a more powerful and comprehensive POI recommendation system. This work first reviews the latest research outcomes that leverage LLMs for POI recommendation, highlighting their contribution to dealing with the long-standing challenges of POI recommendation systems. Furthermore, we identify untapped potentials of LLM-based POI recommenders across the recommendation pipeline, encompassing multimodal feature augmentation, unified encoding, hybrid task learning for scoring and ranking, and dynamic user interaction. By exploring these opportunities, future research can transform POI recommendation systems into adaptive, user-centric assistants, delivering seamless, scalable, and personalized experiences. This article aims to provide a comprehensive overview of recent advancements and propose future directions for leveraging LLMs to redefine the next generation of POI recommendation systems.
- 2 April 2025
- Published by Elsevier in Information Processing & Management
- Vol. 62 (4)
Heterogeneous network for Hierarchical Fine-Grained Domain Fake News Detection
- 2 April 2025
- Published by Elsevier in Information Processing & Management
- Vol. 62 (4)
Heterogeneous network for Hierarchical Fine-Grained Domain Fake News Detection