100 citations · 216 across the 12 of their papers we have counts for
12 papers
Granular-ball Representation Learning for Deep CNN on Learning with Label Noise
Dawei Dai, Hao Zhu, Shuyin Xia +1
In actual scenarios, whether manually or automatically annotated, label noise is inevitably generated in the training data, which can affect the effectiveness of deep CNN models. T…
Tree-based Ensemble Learning for Out-of-distribution Detection
Zhaiming Shen, Menglun Wang, Guang Cheng +5
Being able to successfully determine whether the testing samples has similar distribution as the training samples is a fundamental question to address before we can safely deploy m…
Understanding and Mitigating Hyperbolic Dimensional Collapse in Graph Contrastive Learning
Yifei Zhang, Hao Zhu, Menglin Yang +4
Learning generalizable self-supervised graph representations for downstream tasks is challenging. To this end, Contrastive Learning (CL) has emerged as a leading approach. The embe…
Transductive Few-shot Learning with Prototype-based Label Propagation by Iterative Graph Refinement
Hao Zhu, Piotr Koniusz
Few-shot learning (FSL) is popular due to its ability to adapt to novel classes. Compared with inductive few-shot learning, transductive models typically perform better as they lev…
Spectral Feature Augmentation for Graph Contrastive Learning and Beyond
Yifei Zhang, Hao Zhu, Zixing Song +2
Although augmentations (e.g., perturbation of graph edges, image crops) boost the efficiency of Contrastive Learning (CL), feature level augmentation is another plausible, compleme…
COSTA: Covariance-Preserving Feature Augmentation for Graph Contrastive Learning
Yifei Zhang, Hao Zhu, Zixing Song +2
Graph contrastive learning (GCL) improves graph representation learning, leading to SOTA on various downstream tasks. The graph augmentation step is a vital but scarcely studied st…
Migrating Face Swap to Mobile Devices: A lightweight Framework and A Supervised Training Solution
Haiming Yu, Hao Zhu, Xiangju Lu +1
Existing face swap methods rely heavily on large-scale networks for adequate capacity to generate visually plausible results, which inhibits its applications on resource-constraint…
Graph-adaptive Rectified Linear Unit for Graph Neural Networks
Yifei Zhang, Hao Zhu, Ziqiao Meng +2
Graph Neural Networks (GNNs) have achieved remarkable success by extending traditional convolution to learning on non-Euclidean data. The key to the GNNs is adopting the neural mes…
Contrastive Laplacian Eigenmaps
Hao Zhu, Ke Sun, Piotr Koniusz
Graph contrastive learning attracts/disperses node representations for similar/dissimilar node pairs under some notion of similarity. It may be combined with a low-dimensional embe…
REFINE: Random RangE FInder for Network Embedding
Hao Zhu, Piotr Koniusz
Network embedding approaches have recently attracted considerable interest as they learn low-dimensional vector representations of nodes. Embeddings based on the matrix factorizati…
Imbalance Robust Softmax for Deep Embeeding Learning
Hao Zhu, Yang Yuan, Guosheng Hu +2
Deep embedding learning is expected to learn a metric space in which features have smaller maximal intra-class distance than minimal inter-class distance. In recent years, one rese…
Additively Homomorphical Encryption based Deep Neural Network for Asymmetrically Collaborative Machine Learning
Yifei Zhang, Hao Zhu
The financial sector presents many opportunities to apply various machine learning techniques. Centralized machine learning creates a constraint which limits further applications i…