Related papers: Neural Collapse by Design: Learning Class Prototyp…
Self-supervised learning (especially contrastive learning) has attracted great interest due to its huge potential in learning discriminative representations in an unsupervised manner. Despite the acknowledged successes, existing contrastive…
Continuous unsupervised representation learning (CURL) research has greatly benefited from improvements in self-supervised learning (SSL) techniques. As a result, existing CURL methods using SSL can learn high-quality representations…
Neural collapse (NC) -- the convergence of penultimate-layer features to a simplex equiangular tight frame -- is well understood at equilibrium, but the dynamics governing its onset remain poorly characterised. We identify a simple and…
What scaling limits govern neural network training dynamics when model size and training time grow in tandem? We show that despite the complex interactions between architecture, training algorithms, and data, compute-optimally trained…
Unsupervised sentence representation learning remains a critical challenge in modern natural language processing (NLP) research. Recently, contrastive learning techniques have achieved significant success in addressing this issue by…
Graph Neural Networks (GNNs) have achieved great success in learning graph representations and thus facilitating various graph-related tasks. However, most GNN methods adopt a supervised learning setting, which is not always feasible in…
Self-supervised learning makes significant progress in pre-training large models, but struggles with small models. Mainstream solutions to this problem rely mainly on knowledge distillation, which involves a two-stage procedure: first…
Recent breakthroughs in semi-supervised semantic segmentation have been developed through contrastive learning. In prevalent pixel-wise contrastive learning solutions, the model maps pixels to deterministic representations and regularizes…
While Contrastive Learning (CL) has revolutionized self-supervised representation learning, its latent representations remain highly entangled and opaque, limiting their interpretability in safety-critical applications. We identify that a…
When training classification models, it expects that the learned features are compact within classes, and can well separate different classes. As the dominant loss function for training classification models, minimizing cross-entropy (CE)…
Class-Incremental Learning (CIL) is a critical capability for real-world applications, enabling learning systems to adapt to new tasks while retaining knowledge from previous ones. Recent advancements in pre-trained models (PTMs) have…
Self-supervised learning approach like contrastive learning is attached great attention in natural language processing. It uses pairs of training data augmentations to build a classification task for an encoder with well representation…
Graph Neural Networks (GNNs) are widely used in collaborative filtering to capture high-order user-item relationships. To address the data sparsity problem in recommendation systems, Graph Contrastive Learning (GCL) has emerged as a…
We propose an intra-class subdivision pixel contrastive learning (SPCL) framework for cardiac image segmentation to address representation contamination at boundaries. The novel concept ``Unconcerned sample'' is proposed to distinguish…
Deep representations have shown promising performance when transferred to downstream tasks in a black-box manner. Yet, their inherent lack of interpretability remains a significant challenge, as these features are often opaque to human…
Recently it has been observed that neural networks exhibit Neural Collapse (NC) during the final stage of training for the classification problem. We empirically show that multivariate regression, as employed in imitation learning and other…
When training overparameterized deep networks for classification tasks, it has been widely observed that the learned features exhibit a so-called "neural collapse" phenomenon. More specifically, for the output features of the penultimate…
In this work, we present Multi-Level Contrastive Learning for Dense Prediction Task (MCL), an efficient self-supervised method for learning region-level feature representation for dense prediction tasks. Our method is motivated by the three…
We propose to train bi-directional neural network language model(NNLM) with noise contrastive estimation(NCE). Experiments are conducted on a rescore task on the PTB data set. It is shown that NCE-trained bi-directional NNLM outperformed…
Learning by contrasting positive and negative samples is a general strategy adopted by many methods. Noise contrastive estimation (NCE) for word embeddings and translating embeddings for knowledge graphs are examples in NLP employing this…