Related papers: Transductive Model Selection under Prior Probabili…
Through solving pretext tasks, self-supervised learning leverages unlabeled data to extract useful latent representations replacing traditional input features in the downstream task. In audio/speech signal processing, a wide range of…
Transfer learning is a machine learning technique that uses previously acquired knowledge from a source domain to enhance learning in a target domain by reusing learned weights. This technique is ubiquitous because of its great advantages…
We present a novel self-taught framework for unsupervised metric learning, which alternates between predicting class-equivalence relations between data through a moving average of an embedding model and learning the model with the predicted…
Large language models (LLMs) exhibit impressive in-context learning (ICL) capabilities, yet the quality of their predictions is fundamentally limited by the few costly labeled demonstrations that can fit into a prompt. Meanwhile, there…
In inductive transfer learning, fine-tuning pre-trained convolutional networks substantially outperforms training from scratch. When using fine-tuning, the underlying assumption is that the pre-trained model extracts generic features, which…
Zero-shot learning has received increasing interest as a means to alleviate the often prohibitive expense of annotating training data for large scale recognition problems. These methods have achieved great success via learning intermediate…
We propose a meta-learning method for semi-supervised learning that learns from multiple tasks with heterogeneous attribute spaces. The existing semi-supervised meta-learning methods assume that all tasks share the same attribute space,…
Speech recognition technologies are gaining enormous popularity in various industrial applications. However, building a good speech recognition system usually requires large amounts of transcribed data, which is expensive to collect. To…
Few-shot node classification is tasked to provide accurate predictions for nodes from novel classes with only few representative labeled nodes. This problem has drawn tremendous attention for its projection to prevailing real-world…
The classification of textual data often yields important information. Most classifiers work in a closed world setting where the classifier is trained on a known corpus, and then it is tested on unseen examples that belong to one of the…
Unsupervised models can provide supplementary soft constraints to help classify new target data under the assumption that similar objects in the target set are more likely to share the same class label. Such models can also help detect…
Semi-supervised learning is a challenging problem which aims to construct a model by learning from a limited number of labeled examples. Numerous methods have been proposed to tackle this problem, with most focusing on utilizing the…
Given a supervised machine learning problem where the training set has been subject to a known sampling bias, how can a model be trained to fit the original dataset? We achieve this through the Bayesian inference framework by altering the…
Semi-supervised learning methods are motivated by the availability of large datasets with unlabeled features in addition to labeled data. Unlabeled data is, however, not guaranteed to improve classification performance and has in fact been…
Understanding model performance on unlabeled data is a fundamental challenge of developing, deploying, and maintaining AI systems. Model performance is typically evaluated using test sets or periodic manual quality assessments, both of…
Obtaining labelled data in a particular context could be expensive and time consuming. Although different algorithms, including unsupervised learning, semi-supervised learning, self-learning have been adopted, the performance of text…
In many machine learning applications, labeled data is scarce and obtaining more labels is expensive. We introduce a new approach to supervising neural networks by specifying constraints that should hold over the output space, rather than…
Pre-training is prevalent in deep learning for vision and text data, leveraging knowledge from other datasets to enhance downstream tasks. However, for tabular data, the inherent heterogeneity in attribute and label spaces across datasets…
In many computer vision classification tasks, class priors at test time often differ from priors on the training set. In the case of such prior shift, classifiers must be adapted correspondingly to maintain close to optimal performance.…
Deep Neural Networks are well known for efficiently fitting training data, yet experiencing poor generalization capabilities whenever some kind of bias dominates over the actual task labels, resulting in models learning "shortcuts". In…