相关论文: Contrastive Representation Learning for Exemplar-G…

Graph representation learning nowadays becomes fundamental in analyzing graph-structured data. Inspired by recent success of contrastive methods, in this paper, we propose a novel framework for unsupervised graph representation learning by…

Capturing emotions within a conversation plays an essential role in modern dialogue systems. However, the weak correlation between emotions and semantics brings many challenges to emotion recognition in conversation (ERC). Even semantically…

We propose $\textbf{MGCL}$, a model-driven graph contrastive learning (GCL) framework that leverages graphons (probabilistic generative models for graphs) to guide contrastive learning by accounting for the data's underlying generative…

Contrastive learning has emerged as an essential approach for self-supervised learning in visual representation learning. The central objective of contrastive learning is to maximize the similarities between two augmented versions of an…

We investigate the possibility of forcing a self-supervised model trained using a contrastive predictive loss to extract slowly varying latent representations. Rather than producing individual predictions for each of the future…

Paraphrase Identification is a fundamental task in Natural Language Processing. While much progress has been made in the field, the performance of many state-of-the-art models often suffer from distribution shift during inference time. We…

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…

Graph contrastive learning (GCL) has become a powerful tool for learning graph data, but its scalability remains a significant challenge. In this work, we propose a simple yet effective training framework called Structural Compression…

Contrastive learning -- a modern approach to extract useful representations from unlabeled data by training models to distinguish similar samples from dissimilar ones -- has driven significant progress in foundation models. In this work, we…

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. In this paper, we show that if we cast a…

Creating 3D content from single-view images is a challenging problem that has attracted considerable attention in recent years. Current approaches typically utilize score distillation sampling (SDS) from pre-trained 2D diffusion models to…

A prominent technique for self-supervised representation learning has been to contrast semantically similar and dissimilar pairs of samples. Without access to labels, dissimilar (negative) points are typically taken to be randomly sampled…

Contrastive learning is a discriminative approach that aims at grouping similar samples closer and diverse samples far from each other. It it an efficient technique to train an encoder generating distinguishable and informative…

Contrastive representation learning has been recently proved to be very efficient for self-supervised training. These methods have been successfully used to train encoders which perform comparably to supervised training on downstream…

Most prior work on exemplar-based syntactically controlled paraphrase generation relies on automatically-constructed large-scale paraphrase datasets, which are costly to create. We sidestep this prerequisite by adapting models from prior…

We propose syntactically controlled paraphrase networks (SCPNs) and use them to generate adversarial examples. Given a sentence and a target syntactic form (e.g., a constituency parse), SCPNs are trained to produce a paraphrase of the…

Generalized zero-shot learning(GZSL) aims to classify samples from seen and unseen labels, assuming unseen labels are not accessible during training. Recent advancements in GZSL have been expedited by incorporating…

Graph contrastive learning (GCL) is a popular method for leaning graph representations by maximizing the consistency of features across augmented views. Traditional GCL methods utilize single-perspective i.e. data or model-perspective)…

Electroencephalography-to-Text generation (EEG-to-Text), which aims to directly generate natural text from EEG signals has drawn increasing attention in recent years due to the enormous potential for Brain-computer interfaces (BCIs).…

As Classifier-Free Guidance (CFG) has proven effective in conditional diffusion model sampling for improved condition alignment, many applications use a negated CFG term to filter out unwanted features from samples. However, simply negating…