Research Highlights

(For a list of recent publications see below)

Fast Fully Dynamic Labelling For Distance Queries

Due to the dynamic nature of real-world networks, such as social networks or web graphs in which a link between two entities may fail or become alive at any time, there is a pressing need to address the shortest path distance problem for dynamic networks. In this article, we propose a fully dynamic labelling method to efficiently update distance labelling. At its core, our method incorporates two building blocks for handling incremental update operations and decremental update operations, respectively.

M. Farhan, Q. Wang, Y. Lin, and B. Mckay

The VLDB Journal, 2021 (paper link)

A Regularized Wasserstein Framework for Graph Kernels

We propose a learning framework for graph kernels which is theoretically grounded on regularizing optimal transport. Regularized Wasserstein (RW) discrepancy can preserve both features and structure of graphs via Wasserstein distances on features and their local variations, local barycenters and global connectivity. Two strongly convex regularization terms are introduced to improve the learning ability. The framework is robust and can guarantee the numerical stability in optimization.

A. Wijesinghe, Q. Wang and S. Gould

IEEE International Conference on Data Mining (ICDM), 2021 (paper link)

Beyond Low-Pass Filters: Adaptive Feature Propagation on Graphs

Many graph neural networks (GNNs) assume local homophily, i.e., strong similarities in local neighborhoods. This assumption however limits the generalizability power of GNNs. To address this limitation, we propose a flexible GNN model, which is capable of handling any graphs without being restricted by their underlying homophily.

S. Li, D. Kim, and Q. Wang

The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD), 2021 (paper link)

Query-by-Sketch: Scaling Shortest Path Graph Queries on Very Large Networks

How to efficiently compute a shortest path graph containing exactly all shortest paths between any arbitrary pair of vertices on complex networks? Shortest path graph manifests itself as a basis for tackling various shortest path related problems, e.g., finding critical edges and vertices whose removal can destroy all shortest paths between two vertices.

Y. Wang, Q. Wang, H. Koehler, and Y. Lin

ACM SIGMOD International Conference on Management of Data (SIGMOD), 2021 (paper link)

Efficient Maintenance of Distance Labelling for Incremental Updates in Large Dynamic Graphs

If a graph is dynamically changing over time, how can we efficiently find the shortest path distance between any two vertices? We propose an online incremental method to efficiently answer distance queries over very large dynamic graphs. We have empirically evaluated the efficiency and scalability of the proposed algorithm over 12 large real-world networks.

M. Farhan and Q. Wang

The 24th International Conference on Extending Database Technology (EDBT), 2021 (paper link)

dK-Projection: Publishing Graph Joint Degree Distribution with Node Differential Privacy

Many networks such as social networks often contain sensitive relationships among individuals, (e.g., friendships and acquaintances) or sensitive attributes of individuals (e.g., age, location and race). We develop a framework for publishing higher-order network statistics, i.e., joint degree distribution, under strong mathematical guarantees of node differential privacy.

M. Iftikhar and Q. Wang

The 25th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), 2021 (paper link)

Episode-Adaptive Embedding Networks for Few-Shot Learning

Few-shot learning has attracted attention recently due to its potential to bridge the gap between the cognition ability of humans and the generalization ability of machine learning models. We propose Episode Adaptive Embedding Networks (EAENs), which leverage the probability distributions of all instances in an episode to extract representative episode-specific features.

F. Liu and Q. Wang

The 25th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), 2021 (paper link)

ErGAN: Generative Adversarial Networks for Entity Resolution

Entity Resolution is an important component of real-world applications in various fields. Inspired by recent advances of generative adversarial networks, we propose a novel deep learning model for entity resolution called ErGAN. This model consists of two key components – a label generator and a discriminator that are optimized alternatively through adversarial learning.

J. Shao, Q. Wang, A. Wijesinghe, and E. Rahm

IEEE International Conference on Data Mining (ICDM), 2020 (paper link)

DFNets: Spectral CNNs for Graphs with Feedback-Looped Filters

We propose a novel spectral convolutional neural network model on graph-structured data, namely Distributed Feedback-Looped Networks (DFNets). This model is incorporated with a robust class of spectral graph filters, called feedback-looped filters, to provide better localization on vertices, while still attaining fast convergence and linear memory requirements.

A. Wijesinghe and Q. Wang

The 33rd Conference on Neural Information Processing Systems (NeurIPS), 2019 (paper link)

A Highly Scalable Labelling Approach for Exact Distance Queries in Complex Networks

Answering exact shortest path distance queries is a fundamental task in graph theory. Despite a tremendous amount of research on the subject, there is still no satisfactory solution that can scale to billion-scale complex networks. We develop a highly scalable solution for answering exact distance queries over massive complex networks.

M. Farhan, Q. Wang, Y. Lin, and B. Mckay

The 22nd International Conference on Extending Database Technology (EDBT), 2019 (paper link)

Knowledge Tracing with Sequential Key-Value Memory Networks

Can machines trace human knowledge like humans? Knowledge tracing (KT) is a fundamental task in a wide range of applications in education. In this work, we propose a novel deep learning KT model, namely Sequential Key-Value Memory Networks (SKVMN), which unifies the strengths of recurrent modelling capacity and memory capacity for modelling student learning.

G. Abdelrahman and Q. Wang

ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2019 (paper link)

Learning to Sample: an Active Learning Framework

Meta-learning algorithms for active learning are emerging as a promising paradigm for learning the “best” active learning strategy. However, current learning-based active learning approaches still require sufficient training data so as to generalize meta-learning models for active learning. This is contrary to the nature of active learning which typically starts with a small number of labeled samples.

J. Shao, Q. Wang and F. Liu

IEEE International Conference on Data Mining (ICDM), 2019 (paper link)

FACH: Fast Algorithm for Detecting Cohesive Hierarchies of Communities in Large Networks

We study the hierarchical community detection problem in large networks and show that this problem is NP-hard. We leverage a fast network sparsification technique to improve the efficiency and scalability of a cut-based algorithm for detecting a cohesive hierarchy of communities in a large-scale network.

M. Rezvani, Q. Wang, and W. Liang

The 11th ACM International Conference on Web Search and Data Mining (WSDM), 2018 (paper link)

 

List of Recent Publications

Fast Fully Dynamic Labelling For Distance Queries
M. Farhan, Q. Wang, Y. Lin, and B. Mckay
The VLDB Journal, 2021 (paper link)

A Regularized Wasserstein Framework for Graph Kernels
A. Wijesinghe, Q. Wang and S. Gould
IEEE International Conference on Data Mining (ICDM), 2021 (paper link)

Beyond Low-Pass Filters: Adaptive Feature Propagation on Graphs
S. Li, D. Kim, and Q. Wang
The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD), 2021 (paper link)

Query-by-Sketch: Scaling Shortest Path Graph Queries on Very Large Networks
Y. Wang, Q. Wang, H. Koehler, and Y. Lin
ACM SIGMOD International Conference on Management of Data (SIGMOD), 2021 (paper link)

Efficient Maintenance of Distance Labelling for Incremental Updates in Large Dynamic Graphs
M. Farhan and Q. Wang
The 24th International Conference on Extending Database Technology (EDBT), 2021 (paper link)

dK-Projection: Publishing Graph Joint Degree Distribution with Node Differential Privacy
M. Iftikhar and Q. Wang
The 25th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), 2021 (paper link)

Episode-Adaptive Embedding Networks for Few-Shot Learning
F. Liu and Q. Wang
The 25th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), 2021 (paper link)

ErGAN: Generative Adversarial Networks for Entity Resolution
J. Shao, Q. Wang, A. Wijesinghe, and E. Rahm
IEEE International Conference on Data Mining (ICDM), 2020 (paper link)

dK-Microaggregation: Anonymizing Graphs with Differential Privacy Guarantees
M. Iftikhar, Q. Wang, and Y. Lin
The 24th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), 2020 (paper link)

Dynamic Chunkwise CNN for Distantly Supervised Relation Extraction
F. Liu and Q. Wang
IEEE International Conference on Big Data (IEEE BigData), 2020 (paper link)

DFNets: Spectral CNNs for Graphs with Feedback-Looped Filters
A. Wijesinghe and Q. Wang
The 33rd Conference on Neural Information Processing Systems (NeurIPS), 2019 (paper link)

A Highly Scalable Labelling Approach for Exact Distance Queries in Complex Networks
M. Farhan, Q. Wang, Y. Lin, and B. Mckay
The 22nd International Conference on Extending Database Technology (EDBT), 2019 (paper link)

Knowledge Tracing with Sequential Key-Value Memory Networks
G. Abdelrahman and Q. Wang
ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2019 (paper link)

Publishing Differentially Private Datasets via Stable Microaggregation
M. Iftikhar, Q. Wang, and Y. Lin
The 22nd International Conference on Extending Database Technology (EDBT), 2019 (paper link)

Learning to Sample: an Active Learning Framework
J. Shao, Q. Wang and F. Liu
IEEE International Conference on Data Mining (ICDM), 2019 (paper link)

Skyblocking for Entity Resolution
J. Shao, Q. Wang and Y. Lin
Information Systems, Volume 85, November 2019 (paper link)

Repairing of Record Linkage: Turing Errors into Insight
Q. Bui-Nguyen, Q. Wang, J. Shao, and D. Vatsalan
The 22nd International Conference on Extending Database Technology (EDBT), 2019 (paper link)

Active Blocking Scheme Learning for Entity Resolution
J. Shao and Q. Wang
The 22nd Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), 2018 (paper link)

FACH: Fast Algorithm for Detecting Cohesive Hierarchies of Communities in Large Networks
M. Rezvani, Q. Wang, and W. Liang
The 11th ACM International Conference on Web Search and Data Mining (WSDM), 2018 (paper link)