9 citations · 12 across the 18 of their papers we have counts for
12 papers · 1 filter
Sanitized Clustering against Confounding Bias
Yinghua Yao, Yuangang Pan, Jing Li +2
Real-world datasets inevitably contain biases that arise from different sources or conditions during data collection. Consequently, such inconsistency itself acts as a confounding…
Earning Extra Performance from Restrictive Feedbacks
Jing Li, Yuangang Pan, Yueming Lyu +3
Many machine learning applications encounter a situation where model providers are required to further refine the previously trained model so as to gratify the specific need of loc…
Coarse-to-Fine Contrastive Learning on Graphs
Peiyao Zhao, Yuangang Pan, Xin Li +3
Inspired by the impressive success of contrastive learning (CL), a variety of graph augmentation strategies have been employed to learn node representations in a self-supervised ma…
Taming Overconfident Prediction on Unlabeled Data from Hindsight
Jing Li, Yuangang Pan, Ivor W. Tsang
Minimizing prediction uncertainty on unlabeled data is a key factor to achieve good performance in semi-supervised learning (SSL). The prediction uncertainty is typically expressed…
TRIP: Refining Image-to-Image Translation via Rival Preferences
Yinghua Yao, Yuangang Pan, Ivor W. Tsang +1
Relative attribute (RA), referring to the preference over two images on the strength of a specific attribute, can enable fine-grained image-to-image translation due to its rich sem…
Differential-Critic GAN: Generating What You Want by a Cue of Preferences
Yinghua Yao, Yuangang Pan, Ivor W. Tsang +1
This paper proposes Differential-Critic Generative Adversarial Network (DiCGAN) to learn the distribution of user-desired data when only partial instead of the entire dataset posse…
Learning Node Representations against Perturbations
Xu Chen, Yuangang Pan, Ivor Tsang +1
Recent graph neural networks (GNN) has achieved remarkable performance in node representation learning. One key factor of GNN's success is the \emph{smoothness} property on node re…
Multi-view Alignment and Generation in CCA via Consistent Latent Encoding
Yaxin Shi, Yuangang Pan, Donna Xu +1
Multi-view alignment, achieving one-to-one correspondence of multi-view inputs, is critical in many real-world multi-view applications, especially for cross-view data analysis prob…
Secure Metric Learning via Differential Pairwise Privacy
Jing Li, Yuangang Pan, Yulei Sui +1
Distance Metric Learning (DML) has drawn much attention over the last two decades. A number of previous works have shown that it performs well in measuring the similarities of indi…
Domain-adversarial Network Alignment
Huiting Hong, Xin Li, Yuangang Pan +1
Network alignment is a critical task to a wide variety of fields. Many existing works leverage on representation learning to accomplish this task without eliminating domain represe…
Probabilistic CCA with Implicit Distributions
Yaxin Shi, Yuangang Pan, Donna Xu +1
Canonical Correlation Analysis (CCA) is a classic technique for multi-view data analysis. To overcome the deficiency of linear correlation in practical multi-view learning tasks, v…
Fast and Robust Rank Aggregation against Model Misspecification
Yuangang Pan, Weijie Chen, Gang Niu +2
In rank aggregation (RA), a collection of preferences from different users are summarized into a total order under the assumption of homogeneity of users. Model misspecification in…