Related papers: Conditional Alignment and Uniformity for Contrasti…

Despite pre-trained language models have proven useful for learning high-quality semantic representations, these models are still vulnerable to simple perturbations. Recent works aimed to improve the robustness of pre-trained models mainly…

Trained classification models can unintentionally lead to biased representations and predictions, which can reinforce societal preconceptions and stereotypes. Existing debiasing methods for classification models, such as adversarial…

Self-supervised contrastive learning offers a means of learning informative features from a pool of unlabeled data. In this paper, we delve into another useful approach -- providing a way of selecting a core-set that is entirely unlabeled.…

Recently, self-supervised learning has attracted attention due to its remarkable ability to acquire meaningful representations for classification tasks without using semantic labels. This paper introduces a self-supervised learning…

High annotation costs are a substantial bottleneck in applying modern deep learning architectures to clinically relevant medical use cases, substantiating the need for novel algorithms to learn from unlabeled data. In this work, we propose…

While internet-scale data often comes in pairs (e.g., audio/image, image/text), we often want to perform inferences over modalities unseen together in the training data (e.g., audio/text). Empirically, this can often be addressed by…

We propose a novel algorithm for learning fair representations that can simultaneously mitigate two notions of disparity among different demographic subgroups in the classification setting. Two key components underpinning the design of our…

Presence of bias (in datasets or tasks) is inarguably one of the most critical challenges in machine learning applications that has alluded to pivotal debates in recent years. Such challenges range from spurious associations between…

Contrastive learning has been extensively studied in sentence embedding learning, which assumes that the embeddings of different views of the same sentence are closer. The constraint brought by this assumption is weak, and a good sentence…

Contrastive learning has achieved great success in self-supervised visual representation learning, but existing approaches mostly ignored spatial information which is often crucial for visual representation. This paper presents…

Contrastive learning has emerged as a cornerstone in recent achievements of unsupervised representation learning. Its primary paradigm involves an instance discrimination task with a mutual information loss. The loss is known as InfoNCE and…

Standard conformal prediction methods provide a marginal coverage guarantee, which means that for a random test point, the conformal prediction set contains the true label with a user-specified probability. In many classification problems,…

The similarity of feature representations plays a pivotal role in the success of problems related to domain adaptation. Feature similarity includes both the invariance of marginal distributions and the closeness of conditional distributions…

Conformal inference provides a rigorous statistical framework for uncertainty quantification in machine learning, enabling well-calibrated prediction sets with precise coverage guarantees for any classification model. However, its reliance…

Collaborative learning enables distributed clients to learn a shared model for prediction while keeping the training data local on each client. However, existing collaborative learning methods require fully-labeled data for training, which…

The success of deep learning methods in medical image segmentation tasks heavily depends on a large amount of labeled data to supervise the training. On the other hand, the annotation of biomedical images requires domain knowledge and can…

Conditional independence (CI) constraints are critical for defining and evaluating fairness in machine learning, as well as for learning unconfounded or causal representations. Traditional methods for ensuring fairness either blindly learn…

Understanding the severity of conditions shown in images in medical diagnosis is crucial, serving as a key guide for clinical assessment, treatment, as well as evaluating longitudinal progression. This paper proposes Con- PrO: a novel…

Contrastive self-supervised learning has attracted significant research attention recently. It learns effective visual representations from unlabeled data by embedding augmented views of the same image close to each other while pushing away…

Distance-based anomaly detection methods rely on compact in-distribution (ID) embeddings that are well separated from anomalies. However, conventional contrastive learning strategies often struggle to achieve this balance, either promoting…