3mformer: Multi-order multi-mode transformer for skeletal action recognition

L Wang, P Koniusz - … of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
Many skeletal action recognition models use GCNs to represent the human body by 3D
body joints connected body parts. GCNs aggregate one-or few-hop graph neighbourhoods …

Mitigating the popularity bias of graph collaborative filtering: A dimensional collapse perspective

Y Zhang, H Zhu, Z Song, P Koniusz… - Advances in Neural …, 2023 - proceedings.neurips.cc
Abstract Graph-based Collaborative Filtering (GCF) is widely used in personalized
recommendation systems. However, GCF suffers from a fundamental problem where …

Optimal block-wise asymmetric graph construction for graph-based semi-supervised learning

Z Song, Y Zhang, I King - Advances in Neural Information …, 2024 - proceedings.neurips.cc
Graph-based semi-supervised learning (GSSL) serves as a powerful tool to model the
underlying manifold structures of samples in high-dimensional spaces. It involves two …

Hyperbolic representation learning: Revisiting and advancing

M Yang, M Zhou, R Ying, Y Chen… - … on Machine Learning, 2023 - proceedings.mlr.press
The non-Euclidean geometry of hyperbolic spaces has recently garnered considerable
attention in the realm of representation learning. Current endeavors in hyperbolic …

Contrastive cross-scale graph knowledge synergy

Y Zhang, Y Chen, Z Song, I King - Proceedings of the 29th ACM SIGKDD …, 2023 - dl.acm.org
Graph representation learning via Contrastive Learning (GCL) has drawn considerable
attention recently. Efforts are mainly focused on gathering more global information via …

Bipartite graph convolutional hashing for effective and efficient top-n search in hamming space

Y Chen, Y Fang, Y Zhang, I King - … of the ACM Web Conference 2023, 2023 - dl.acm.org
Searching on bipartite graphs is basal and versatile to many real-world Web applications,
eg, online recommendation, database retrieval, and query-document searching. Given a …

A survey of trustworthy federated learning with perspectives on security, robustness and privacy

Y Zhang, D Zeng, J Luo, Z Xu, I King - … of the ACM Web Conference 2023, 2023 - dl.acm.org
Trustworthy artificial intelligence (AI) technology has revolutionized daily life and greatly
benefited human society. Among various AI technologies, Federated Learning (FL) stands …

No change, no gain: empowering graph neural networks with expected model change maximization for active learning

Z Song, Y Zhang, I King - Advances in Neural Information …, 2024 - proceedings.neurips.cc
Abstract Graph Neural Networks (GNNs) are crucial for machine learning applications with
graph-structured data, but their success depends on sufficient labeled data. We present a …

Graph contrastive learning with stable and scalable spectral encoding

D Bo, Y Fang, Y Liu, C Shi - Advances in Neural …, 2024 - proceedings.neurips.cc
Graph contrastive learning (GCL) aims to learn representations by capturing the agreements
between different graph views. Traditional GCL methods generate views in the spatial …

Learning partial correlation based deep visual representation for image classification

S Rahman, P Koniusz, L Wang… - Proceedings of the …, 2023 - openaccess.thecvf.com
Visual representation based on covariance matrix has demonstrates its efficacy for image
classification by characterising the pairwise correlation of different channels in convolutional …