Related papers: Instructor-inspired Machine Learning for Robust Mo…

Transductive learning is a supervised machine learning task in which, unlike in traditional inductive learning, the unlabelled data that require labelling are a finite set and are available at training time. Similarly to inductive learning…

Recent work on distilling Whisper's knowledge into small models using pseudo-labels shows promising performance while reducing the size by up to 50%. This results in small, efficient, and dedicated models. However, a critical step of…

In supervised machine learning, models are typically trained using data with hard labels, i.e., definite assignments of class membership. This traditional approach, however, does not take the inherent uncertainty in these labels into…

The great success that deep models have achieved in the past is mainly owed to large amounts of labeled training data. However, the acquisition of labeled data for new tasks aside from existing benchmarks is both challenging and costly.…

Partial label learning is a type of weakly supervised learning, where each training instance corresponds to a set of candidate labels, among which only one is true. In this paper, we introduce ProPaLL, a novel probabilistic approach to this…

Recent advances in diffusion models have shown remarkable potential in the conditional generation of novel molecules. These models can be guided in two ways: (i) explicitly, through additional features representing the condition, or (ii)…

We propose a general purpose active learning algorithm for structured prediction, gathering labeled data for training a model that outputs a set of related labels for an image or video. Active learning starts with a limited initial training…

A key challenge for machine intelligence is to learn new visual concepts without forgetting the previously acquired knowledge. Continual learning is aimed towards addressing this challenge. However, there is a gap between existing…

Self-supervised learning, which learns by constructing artificial labels given only the input signals, has recently gained considerable attention for learning representations with unlabeled datasets, i.e., learning without any…

Learning skills by imitation is a promising concept for the intuitive teaching of robots. A common way to learn such skills is to learn a parametric model by maximizing the likelihood given the demonstrations. Yet, human demonstrations are…

Recent deep networks are capable of memorizing the entire data even when the labels are completely random. To overcome the overfitting on corrupted labels, we propose a novel technique of learning another neural network, called MentorNet,…

Fine-grained robot manipulation, such as lifting and rotating a bottle to display the label on the cap, requires robust reasoning about object parts and their relationships with intended tasks. Despite recent advances in training…

The ability of Large Language Models (LLMs) to precisely follow complex and fine-grained lexical instructions is a cornerstone of their utility and controllability. However, evaluating this capability remains a significant challenge.…

In biomedical studies, it is often desirable to characterize the interactive mode of multiple disease outcomes beyond their marginal risk. Ising model is one of the most popular choices serving for this purpose. Nevertheless, learning…

Chemists in search of structure-property relationships face great challenges due to limited high quality, concordant datasets. Machine learning (ML) has significantly advanced predictive capabilities in chemical sciences, but these modern…

Molecular representation learning is pivotal for various molecular property prediction tasks related to drug discovery. Robust and accurate benchmarks are essential for refining and validating current methods. Existing molecular property…

Meta-learning is an effective method to handle imbalanced and noisy-label learning, but it depends on a validation set containing randomly selected, manually labelled and balanced distributed samples. The random selection and manual…

Enhancing the instruction-following ability of Large Language Models (LLMs) primarily demands substantial instruction-tuning datasets. However, the sheer volume of these imposes a considerable computational burden and annotation cost. To…

Semi-supervised learning (SSL) has been proposed to leverage unlabeled data for training powerful models when only limited labeled data is available. While existing SSL methods assume that samples in the labeled and unlabeled data share the…

Contrastive, self-supervised learning (SSL) is used to train a model that predicts cancer type from miRNA, mRNA or RPPA expression data. This model, a pretrained FT-Transformer, is shown to outperform XGBoost and CatBoost, standard…