Shirui Pan is a Professor and an ARC Future Fellow with the School of Information and Communication Technology, Griffith University, Australia. Before joining Griffith in 2022, he was with the Faculty of Information Technology, Monash University. He received his Ph.D degree in computer science from University of Technology Sydney (UTS), Australia. He is a Senior Member of IEEE and ACM, and a Fellow of Queensland Academy of Arts and Sciences (FQA).
Shirui’s research mainly focuses on artificial intelligence (AI), data mining, and machine learning. He has made contributions to advance graph machine learning methods for solving hard AI problems for real-life applications, including graph classification, anomaly detection, recommender systems, and multivariate time series forecasting. His research has been published in top conferences and journals including NeurIPS, ICML, KDD, TPAMI, TNNLS, and TKDE. He is recognised as one of the AI 2000 AAAI/IJCAI Most Influential Scholars in Australia (2023, 2022), and one of the World’s Top 2% Scientists (2022, 2021). His research received the IEEE ICDM Best Student Paper Award (2020), and the JCDL Best Paper Honorable Mention Award (2020). He has eight papers recognised as the Most Influential Papers in KDD (x1), IJCAI (x5), AAAI (x1), and CIKM (x1) (Feb 2022). He received a prestigious Future Fellowship (2022-2025), one of the most competitive grants from the Australian Research Council (ARC).
PhD positions are open! I am looking for self-motivated Ph.D students. See more information here.
Interests
- Artificial Intelligence
- Data Mining
- Machine Learning
- Deep Learning
- NLP
- Graph and Network Analysis
Education
-
PhD in Computer Science
University of Technology Sydney
Latest
- GNNEvaluator: Evaluating GNN Performance On Unseen Graphs Without Labels
- Structure-free Graph Condensation: From Large-scale Graphs to Condensed Graph-free Data
- Towards Self-Interpretable Graph-Level Anomaly Detection
- Towards Few-shot Inductive Link Prediction on Knowledge Graphs: A Relational Anonymous Walk-guided Neural Process Approach
- Domain-adaptive Graph Attention-supervised Network for Cross-network Edge Classification
- Towards Flexible and Adaptive Neural Process for Cold-Start Recommendation
- Unifying Large Language Models and Knowledge Graphs: A Roadmap
- Learning Strong Graph Neural Networks with Weak Information
- A Survey on Fairness-aware Recommender Systems
- A Survey on Neural-symbolic Learning Systems
- Boosting Graph Contrastive Learning via Adaptive Sampling
- G2Pxy: Generative Open-Set node Classification on Graphs with Proxy Unknowns
- Demystifying Uneven Vulnerability of Link Stealing Attacks against Graph Neural Networks
- Finding the Missing-half: Graph Complementary Learning for Homophily-prone and Heterophily-prone Graphs
- Normalizing Flow-based Neural Process for Few-Shot Knowledge Graph Completion
- Spatio-Temporal Joint Graph Convolutional Networks for Traffic Forecasting
- Auto-HeG: Automated Graph Neural Network on Heterophilic Graphs
- Dual Intent Enhanced Graph Neural Network for Session-based New Item Recommendation
- Robust Graph Representation Learning for Local Corruption Recovery
- MAMDR: A Model Agnostic Learning Method for Multi-Domain Recommendation
- TxAllo: Dynamic Transaction Allocation in Sharded Blockchain Systems
- Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminating
- Graph Sequential Neural ODE Process for Link Prediction on Dynamic and Sparse Graphs
- Neighbor Contrastive Learning on Learnable Graph Augmentation
- Simple and Efficient Heterogeneous Graph Neural Network
- GOOD-D: On Unsupervised Graph Out-Of-Distribution Detection
- Contrastive Graph Similarity Networks
- Neural Temporal Walks: Motif-Aware Representation Learning on Continuous-Time Dynamic Graphs
- Pseudo-Riemannian Graph Convolutional Networks
- Rethinking and Scaling Up Graph Contrastive Learning: An Extremely Efficient Approach with Group Discrimination
- A Dynamic Variational Framework for Open-World Node Classification in Structured Sequences
- How Far are We from Robust Long Abstractive Summarization?
- Multi-Relational Graph Neural Architecture Search with Fine-grained Message Passing
- Unifying Graph Contrastive Learning with Flexible Contextual Scopes
- An Empirical Survey on Long Document Summarization: Datasets, Models and Metrics
- Beyond low-pass filtering: Graph convolutional networks with automatic filtering
- Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs
- Projective Ranking-based GNN Evasion Attacks
- Reinforced, Incremental and Cross-lingual Event Detection From Social Messages
- Robust Physical-World Attacks on Face Recognition
- Towards Graph Self-Supervised Learning with Contrastive Adjusted Zooming
- TraverseNet: Unifying Space and Time in Message Passing for Traffic Forecasting
- Ultrahyperbolic Knowledge Graph Embeddings
- Graph self-supervised learning: A survey
- CGMN: A Contrastive Graph Matching Network for Self-Supervised Graph Similarity Learning
- Multi-Graph Fusion Networks for Urban Region Embedding
- Survey on Graph Neural Network Acceleration: An Algorithmic Perspective
- Triformer: Triangular, Variable-Specific Attentions for Long Sequence Multivariate Time Series Forecasting
- A Probabilistic Graphical Model Based on Neural-symbolic Reasoning for Visual Relationship Detection
- BaLeNAS: Differentiable Architecture Search via Bayesian Learning Rule
- Cross-modal Clinical Graph Transformer For Ophthalmic Report Generation
- Towards Spatio-Temporal Aware Traffic Time Series Forecasting
- Model Extraction Attacks on Graph Neural Networks: Taxonomy and Realisation
- Predicting Best-Selling New Products in a Major Promotion Campaign through Graph Convolutional Networks
- Fire Burns, Swords Cut: Commonsense Inductive Bias for Exploration in Text-based Games
- Attraction and Repulsion: Unsupervised Domain Adaptive Graph Contrastive Learning Network
- Learning multi-level weight-centric features for few-shot learning
- GCNFusion: An efficient graph convolutional network based model for information diffusion
- Dual Space Graph Contrastive Learning
- Towards Unsupervised Deep Graph Structure Learning
- Predicting Human Mobility via Graph Convolutional Dual-attentive Networks
- Exploring Relational Semantics for Inductive Knowledge Graph Completion
- Discrete Embedding for Attributed Graphs
- Anomaly Detection in Dynamic Graphs via Transformer
- Contrastive Graph Poisson Networks: Semi-Supervised Learning with Extremely Limited Labels
- One-shot Learning-based Animal Video Segmentation
- Adapting Membership Inference Attacks to GNN for Graph Classification: Approaches and Implications
- Hypergraph Convolutional Network for Group Recommendation
- Deep Learning Data Augmentation for Raman Spectroscopy Cancer Tissue Classification
- Learning Graph Representations with Maximal Cliques
- ANEMONE: Graph Anomaly Detection with Multi-Scale Contrastive Learning
- Leveraging Information Bottleneck for Scientific Document Summarization
- Projective Ranking: A Transferable Evasion Attack Method on Graph Neural Networks
- Deep Neighbor-aware Embedding for Node Clustering in Attributed Graphs
- A Survey of Community Detection Approaches: From Statistical Modeling to Deep Learning
- Cyclic label propagation for graph semi-supervised learning
- OpenWGL: Open-World Graph Learning for Unseen Class Node Classification
- Temporal Network Embedding for Link Prediction via VAE joint Attention Mechanism
- iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients
- Medical Code Assignment with Gated Convolution and Note-Code Interaction
- Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learning
- Dual Interactive Graph Convolutional Networks for Hyperspectral Image Classification
- Heterogeneous Graph Attention Network for Small and Medium-Sized Enterprises Bankruptcy Prediction
- A Survey on Knowledge Graphs: Representation, Acquisition and Applications
- Graph Learning: A Survey
- Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning
- Convolutional Neural Networks based Lung Nodule Classification: A Surrogate-Assisted Evolutionary Algorithm for Hyperparameter Optimization
- Learning Graph Neural Networks with Positive and Unlabeled Nodes
- Task-adaptive Neural Process for User Cold-Start Recommendation
- Contrastive and Generative Graph Convolutional Networks for Graph-based Semi-Supervised Learning
- Compact Scheduling for Task Graph Oriented Mobile Crowdsourcing
- One-Shot Neural Architecture Search: Maximising Diversity to Overcome Catastrophic Forgetting
- Differentiable Neural Architecture Search in Equivalent Space with Exploration Enhancement
- Graph Geometry Interaction Learning
- Graph Stochastic Neural Networks for Semi-supervised Learning
- Suicidal Ideation Detection: A Review of Machine Learning Methods and Applications
- Cross-Graph: Robust and Unsupervised Embedding for Attributed Graphs with Corrupted Structure
- OpenWGL: Open-World Graph Learning
- Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks
- Grounding Visual Concepts for Multimedia Event Detection and Multimedia Event Captioning in Zero-shot Setting
- Multivariate Relations Aggregation Learning in Social Networks
- Hyperspectral Image Classification with Context-aware Dynamic Graph Convolutional Networks
- A Relation-Specific Attention Network for Joint Entity and Relation Extraction
- One-Shot Neural Architecture Search via Novelty Driven Sampling
- Reasoning Like Human: Hierarchical Reinforcement Learning for Knowledge Graph Reasoning
- A comprehensive survey on graph neural networks
- Overcoming Multi-Model Forgetting in One-Shot NAS with Diversity Maximization
- Unsupervised Domain Adaptive Graph Convolutional Networks
- Going Deep: Graph Convolutional Ladder-shape Networks
- GSSNN: Graph Smoothing Splines Neural Networks
- Reinforcement Learning based Meta-path Discovery in Large-scale Heterogeneous Information Networks
- Clustering Social Audiences in Business Information Networks
- Familial Clustering For Weakly-labeled Android Malware Using Hybrid Representation Learning
- Adaptive knowledge subgraph ensemble for robust and trustworthy knowledge graph completion
- An Effective and Explainable Deep Fusion Network for Affect Recognition Using Physiological Signals
- Domain-Adversarial Graph Neural Networks for Text Classification
- Learning Graph Embedding With Adversarial Training Methods
- Long-short Distance Aggregation Networks for Positive Unlabeled Graph Learning
- Relation Structure-Aware Heterogeneous Graph Neural Network
- Exploiting Implicit Influence from Information Propagation for Social Recommendation
- Attributed Graph Clustering: A Deep Attentional Embedding Approach
- Graph WaveNet for Deep Spatial-Temporal Graph Modeling
- Influence Spread in Geo-Social Networks: A Multi-Objective Optimization Perspective
- Low-Bit Quantization for Attributed Network Representation Learning
- CFOND: consensus factorization for co-clustering networked data
- Cost-sensitive parallel learning framework for insurance intelligence operation
- Detecting Suicidal Ideation with Data Protection in Online Communities
- Identify topic relations in scientific literature using topic modeling
- IEEE access special section editorial: advanced data analytics for large-scale complex data environments
- Label Embedding with Partial Heterogeneous Contexts
- Measuring distance-based semantic similarity using meronymy and hyponymy relations
- Social recommendation with evolutionary opinion dynamics
- Time series feature learning with labeled and unlabeled data
- A hybrid user experience evaluation method for mobile games
- A three-layered mutually reinforced model for personalized citation recommendation
- Active discriminative network representation learning
- Advances in processing, mining, and learning complex data: From foundations to real-world applications
- Adversarially regularized graph autoencoder for graph embedding
- Binarized attributed network embedding
- Cost-sensitive hybrid neural networks for heterogeneous and imbalanced data
- Cross-domain deep learning approach for multiple financial market prediction
- DiSAN: directional self-attention network for RNN/CNN-free language understanding
- Discrete network embedding
- Explore semantic topics and author communities for citation recommendation in bipartite bibliographic network
- FraudNE: a joint embedding approach for fraud detection
- Hashing for adaptive real-time graph stream classification with concept drifts
- Heterogeneous information network embedding based personalized query-focused astronomy reference paper recommendation
- Low-rank and sparse matrix factorization for scientific paper recommendation in heterogeneous network
- Multi-instance learning with discriminative bag mapping
- Multiple structure-view learning for graph classification
- Query-oriented citation recommendation based on network correlation
- Supervised learning for suicidal ideation detection in online user content
- Boosting for graph classification with universum
- Graph ladder networks for network classification
- MGAE: marginalized graph autoencoder for graph clustering
- Multi-document summarization based on sentence cluster using Non-negative Matrix Factorization
- Positive and unlabeled multi-graph learning
- Task sensitive feature exploration and learning for multitask graph classification
- Towards large-scale social networks with online diffusion provenance detection
- Universal network representation for heterogeneous information networks
- Classifying networked text data with positive and unlabeled examples
- Co-clustering enterprise social networks
- Direct discriminative bag mapping for multi-instance learning
- Iterative views agreement: an iterative low-rank based structured optimization method to multi-view spectral clustering
- Joint structure feature exploration and regularization for multi-task graph classification
- Multi-graph-view subgraph mining for graph classification
- SODE: Self-adaptive one-dependence estimators for classification
- Tri-party deep network representation
- Boosting for multi-graph classification
- CogBoost: boosting for fast cost-sensitive graph classification
- Finding the best not the most: regularized loss minimization subgraph selection for graph classification
- Graph ensemble boosting for imbalanced noisy graph stream classification
- Locally weighted learning: how and when does it work in Bayesian networks?
- Mining top-k minimal redundancy frequent patterns over uncertain databases
- Multi-graph-view learning for complicated object classification
- Multi-graph-view Learning for Graph Classification
- Self-adaptive attribute weighting for Naive Bayes classification
- Attribute weighting: how and when does it work for Bayesian Network Classification
- Dual instance and attribute weighting for Naive Bayes classification
- Exploring features for complicated objects: cross-view feature selection for multi-instance learning
- Multi-graph learning with positive and unlabeled bags
- Graph classification with imbalanced class distributions and noise
- Graph stream classification using labeled and unlabeled graphs
- CGStream: Continuous correlated graph query for data streams
- Continuous top-k query for graph streams
- Dynamic classifier ensemble for positive unlabeled text stream classification
- Top-k correlated subgraph query for data streams
- Classifier ensemble for uncertain data stream classification
- Ensemble of multiple descriptors for automatic image annotation