Related papers: Learning Robust Representations for Malicious Cont…

We focus on a relatively unexplored learning paradigm known as {\em Online Unsupervised Continual Learning} (O-UCL), where an agent receives a non-stationary, unlabeled data stream and progressively learns to identify an increasing number…

The cold-start problem is a long-standing challenge in recommender systems. As a promising solution, content-based generative models usually project a cold-start item's content onto a warm-start item embedding to capture collaborative…

Multi-label image classification presents a challenging task in many domains, including computer vision and medical imaging. Recent advancements have introduced graph-based and transformer-based methods to improve performance and capture…

Well-annotated medical datasets enable deep neural networks (DNNs) to gain strong power in extracting lesion-related features. Building such large and well-designed medical datasets is costly due to the need for high-level expertise. Model…

Unsupervised Camouflaged Object Detection (UCOD) remains a challenging task due to the high intrinsic similarity between target objects and their surroundings, as well as the reliance on noisy pseudo-labels that hinder fine-grained texture…

Recommending cold-start items is a long-standing and fundamental challenge in recommender systems. Without any historical interaction on cold-start items, CF scheme fails to use collaborative signals to infer user preference on these items.…

With the rapid advancement of multi-modal large language models (MLLMs) in recent years, the foundational Contrastive Language-Image Pretraining (CLIP) framework has been successfully extended to MLLMs, enabling more powerful and universal…

Real-world multimodal systems routinely face missing-input scenarios, and in reality, robots lose audio in a factory or a clinical record omits lab tests at inference time. Standard fusion layers either preserve robustness or calibration…

Contrastive learning has achieved remarkable success in representation learning via self-supervision in unsupervised settings. However, effectively adapting contrastive learning to supervised learning tasks remains as a challenge in…

From only positive (P) and unlabeled (U) data, a binary classifier could be trained with PU learning, in which the state of the art is unbiased PU learning. However, if its model is very flexible, empirical risks on training data will go…

We propose a unified representation learning framework to address the Cross Model Compatibility (CMC) problem in the context of visual search applications. Cross compatibility between different embedding models enables the visual search…

Weakly supervised semantic segmentation (WSSS) methods using class labels often rely on class activation maps (CAMs) to localize objects. However, traditional CAM-based methods struggle with partial activations and imprecise object…

Deterministic embeddings learned by contrastive learning (CL) methods such as SimCLR and SupCon achieve state-of-the-art performance but lack a principled mechanism for uncertainty quantification. We propose Variational Contrastive Learning…

Semi-supervised learning frameworks usually adopt mutual learning approaches with multiple submodels to learn from different perspectives. To avoid transferring erroneous pseudo labels between these submodels, a high threshold is usually…

Contrastive learning has achieved remarkable success in learning effective representations, with supervised contrastive learning often outperforming self-supervised approaches. However, in real-world scenarios, data annotations are often…

While numerous machine unlearning (MU) methods have recently been developed with promising results in erasing the influence of forgotten data, classes, or concepts, they are also highly vulnerable-for example, simple fine-tuning can…

As machine learning (ML) models are increasingly deployed in high-stakes domains, trustworthy uncertainty quantification (UQ) is critical for ensuring the safety and reliability of these models. Traditional UQ methods rely on specifying a…

Graph Neural Network (GNN)-based models have become the mainstream approach for recommender systems. Despite the effectiveness, they are still suffering from the cold-start problem, i.e., recommend for few-interaction items. Existing…

We introduce a framework for robust uncertainty quantification in situations where labeled training data are corrupted, through noisy or missing labels. We build on conformal prediction, a statistical tool for generating prediction sets…

Contrastive learning (CL) aims to preserve relational structure between samples by learning representations that reflect a similarity graph. Yet, the geometry of the resulting embeddings remains poorly understood. Here we show that weighted…