相关论文: MEMENTO: Leveraging Web as a Learning Signal for L…

Meta-training, which fine-tunes the language model (LM) on various downstream tasks by maximizing the likelihood of the target label given the task instruction and input instance, has improved the zero-shot task generalization performance.…

The advances in deep learning have enabled machine learning methods to outperform human beings in various areas, but it remains a great challenge for a well-trained model to quickly adapt to a new task. One promising solution to realize…

The transition from stateless language model inference to persistent, multi session autonomous agents has revealed memory to be a primary architectural bottleneck in the deployment of production grade agentic systems. Existing methodologies…

Label error is a ubiquitous problem in annotated data. Large amounts of label error substantially degrades the quality of deep learning models. Existing methods to tackle the label error problem largely focus on the classification task, and…

Unsupervised learning has been an attractive method for easily deriving meaningful data representations from vast amounts of unlabeled data. These representations, or embeddings, often yield superior results in many tasks, whether used…

The online meta-learning framework has arisen as a powerful tool for the continual lifelong learning setting. The goal for an agent is to quickly learn new tasks by drawing on prior experience, while it faces with tasks one after another.…

For languages with no annotated resources, transferring knowledge from rich-resource languages is an effective solution for named entity recognition (NER). While all existing methods directly transfer from source-learned model to a target…

Machine learning practitioners often have access to a spectrum of data: labeled data for the target task (which is often limited), unlabeled data, and auxiliary data, the many available labeled datasets for other tasks. We describe TAGLETS,…

Active learners alleviate the burden of labeling large amounts of data by detecting and asking the user to label only the most informative examples in the domain. We focus here on active learning for multi-view domains, in which there are…

Text categorization is an essential task in Web content analysis. Considering the ever-evolving Web data and new emerging categories, instead of the laborious supervised setting, in this paper, we focus on the minimally-supervised setting…

Interpretability and effectiveness are two essential and indispensable requirements for adopting machine learning methods in reality. In this paper, we propose a knowledge distillation based decision trees extension, dubbed rectified…

Incorporating metadata in Large Language Models (LLMs) pretraining has recently emerged as a promising approach to accelerate training. However prior work highlighted only one useful signal-URLs, leaving open the question of whether other…

The lack of labeled data is a common challenge in speech classification tasks, particularly those requiring extensive subjective assessment, such as cognitive state classification. In this work, we propose a Semi-Supervised Learning (SSL)…

Image search and retrieval engines rely heavily on textual annotation in order to match word queries to a set of candidate images. A system that can automatically annotate images with meaningful text can be highly beneficial for such…

The development of audio event recognition systems require labeled training data, which are generally hard to obtain. One promising source of recordings of audio events is the large amount of multimedia data on the web. In particular, if…

The paradigm of training models on massive data without label through self-supervised learning (SSL) and finetuning on many downstream tasks has become a trend recently. However, due to the high training costs and the unconsciousness of…

Unsupervised meta-learning aims to learn generalizable knowledge across a distribution of tasks constructed from unlabeled data. Here, the main challenge is how to construct diverse tasks for meta-learning without label information; recent…

Practical autonomous driving systems face two crucial challenges: memory constraints and domain gap issues. In this paper, we present a novel approach to learn domain adaptive knowledge in models with limited memory, thus bestowing the…

In the weakly supervised learning paradigm, labeling functions automatically assign heuristic, often noisy, labels to data samples. In this work, we provide a method for learning from weak labels by separating two types of complementary…

High annotation costs are a major bottleneck for the training of semantic segmentation systems. Therefore, methods working with less annotation effort are of special interest. This paper studies the problem of semi-supervised semantic…