Related papers: Negatives-Dominant Contrastive Learning for Genera…
Contrastive learning is a representation learning method performed by contrasting a sample to other similar samples so that they are brought closely together, forming clusters in the feature space. The learning process is typically…
Despite its empirical success, the theoretical foundations of self-supervised contrastive learning (CL) are not yet fully established. In this work, we address this gap by showing that standard CL objectives implicitly approximate a…
To adapt effectively to dynamic real-world environments, intelligent systems must continually acquire new skills while generalizing them to diverse, unseen scenarios. Here, we introduce a novel and realistic setting named domain…
Contrastive Learning (CL)-based recommender systems have gained prominence in the context of Heterogeneous Graph (HG) due to their capacity to enhance the consistency of representations across different views. However, existing frameworks…
Contrastive learning (CL) is one of the most successful paradigms for self-supervised learning (SSL). In a principled way, it considers two augmented "views" of the same image as positive to be pulled closer, and all other images as…
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…
Domain Generalization (DG) is a fundamental challenge for machine learning models, which aims to improve model generalization on various domains. Previous methods focus on generating domain invariant features from various source domains.…
Graph contrastive learning (GCL) alleviates the heavy reliance on label information for graph representation learning (GRL) via self-supervised learning schemes. The core idea is to learn by maximising mutual information for similar…
Continual learning (CL) involves acquiring and accumulating knowledge from evolving tasks while alleviating catastrophic forgetting. Recently, leveraging contrastive loss to construct more transferable and less forgetful representations has…
Aiming to generalize the well-trained gaze estimation model to new target domains, Cross-domain Gaze Estimation (CDGE) is developed for real-world application scenarios. Existing CDGE methods typically extract the domain-invariant features…
Fine-grained classification involves dealing with datasets with larger number of classes with subtle differences between them. Guiding the model to focus on differentiating dimensions between these commonly confusable classes is key to…
Deep learning based task systems normally rely on a large amount of manually labeled training data, which is expensive to obtain and subject to operator variations. Moreover, it does not always hold that the manually labeled data and the…
Graph contrastive learning (GCL) aims to learn representations from unlabeled graph data in a self-supervised manner and has developed rapidly in recent years. However, edgelevel contrasts are not well explored by most existing GCL methods.…
In-Context Learning (ICL) is an important paradigm for adapting Large Language Models (LLMs) to downstream tasks through a few demonstrations. Despite the great success of ICL, the limitation of the demonstration number may lead to…
Deep learning based medical imaging classification models usually suffer from the domain shift problem, where the classification performance drops when training data and real-world data differ in imaging equipment manufacturer, image…
Multimodal Domain Generalization (MMDG) leverages the complementary strengths of multiple modalities to enhance model generalization on unseen domains. A central challenge in multimodal learning is optimization imbalance, where modalities…
Diabetic Retinopathy (DR) constitutes 5% of global blindness cases. While numerous deep learning approaches have sought to enhance traditional DR grading methods, they often falter when confronted with new out-of-distribution data thereby…
With the prosperity of contrastive learning for visual representation learning (VCL), it is also adapted to the graph domain and yields promising performance. However, through a systematic study of various graph contrastive learning (GCL)…
Learning representations of images that are invariant to sensitive or unwanted attributes is important for many tasks including bias removal and cross domain retrieval. Here, our objective is to learn representations that are invariant to…
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…