Search Results for author:
Found 11 papers, 5 papers with code
A Message Passing Perspective on Learning Dynamics of Contrastive Learning
In recent years, contrastive learning achieves impressive results on self-supervised visual representation learning, but there still lacks a rigorous understanding of its learning dynamics.
Optimization-Induced Graph Implicit Nonlinear Diffusion
Moreover, we show that the optimization-induced variants of our models can boost the performance and improve training stability and efficiency as well.
Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation Overlap
Our theory suggests an alternative understanding of contrastive learning: the role of aligning positive samples is more like a surrogate task than an ultimate goal, and the overlapped augmented views (i. e., the chaos) create a ladder for contrastive learning to gradually learn class-separated representations.
A Unified Contrastive Energy-based Model for Understanding the Generative Ability of Adversarial Training
On the other hand, our unified framework can be extended to the unsupervised scenario, which interprets unsupervised contrastive learning as an important sampling of CEM.
Residual Relaxation for Multi-view Representation Learning
Multi-view methods learn representations by aligning multiple views of the same image and their performance largely depends on the choice of data augmentation.
Chaos is a Ladder: A New Understanding of Contrastive Learning
Our work suggests an alternative understanding of contrastive learning: the role of aligning positive samples is more like a surrogate task than an ultimate goal, and it is the overlapping augmented views (i. e., the chaos) that create a ladder for contrastive learning to gradually learn class-separated representations.
Reparameterized Sampling for Generative Adversarial Networks
Recently, sampling methods have been successfully applied to enhance the sample quality of Generative Adversarial Networks (GANs).
Demystifying Adversarial Training via A Unified Probabilistic Framework
Based on these, we propose principled adversarial sampling algorithms in both supervised and unsupervised scenarios.
Dissecting the Diffusion Process in Linear Graph Convolutional Networks
Graph Convolutional Networks (GCNs) have attracted more and more attentions in recent years.
Efficient Sampling for Generative Adversarial Networks with Coupling Markov Chains
Recently, sampling methods have been successfully applied to enhance the sample quality of Generative Adversarial Networks (GANs).
Decoder-free Robustness Disentanglement without (Additional) Supervision
Adversarial Training (AT) is proposed to alleviate the adversarial vulnerability of machine learning models by extracting only robust features from the input, which, however, inevitably leads to severe accuracy reduction as it discards the non-robust yet useful features.
