Related papers: Towards more Reliable Transfer Learning

The standard closed-set domain adaptation approaches seek to mitigate distribution discrepancies between two domains under the constraint of both sharing identical label sets. However, in realistic scenarios, finding an optimal source…

Recent works of multi-source domain adaptation focus on learning a domain-agnostic model, of which the parameters are static. However, such a static model is difficult to handle conflicts across multiple domains, and suffers from a…

Domain adaptation is critical for learning in new and unseen environments. With domain adversarial training, deep networks can learn disentangled and transferable features that effectively diminish the dataset shift between the source and…

Deep learning techniques are renowned for supporting effective transfer learning. However, as we demonstrate, the transferred representations support only a few modes of separation and much of its dimensionality is unutilized. In this work,…

Theoretical studies on transfer learning or domain adaptation have so far focused on situations with a known hypothesis class or model; however in practice, some amount of model selection is usually involved, often appearing under the…

Memory-based self-evolution has emerged as a promising paradigm for coding agents. However, existing approaches typically restrict memory utilization to homogeneous task domains, failing to leverage the shared infrastructural foundations,…

Multitask learning is widely used in practice to train a low-resource target task by augmenting it with multiple related source tasks. Yet, naively combining all the source tasks with a target task does not always improve the prediction…

In many practical data mining scenarios, such as network intrusion detection, Twitter spam detection, and computer-aided diagnosis, a source domain that is different from but related to a target domain is very common. In addition, a large…

This paper addresses the problem of transferring useful knowledge from a source network to predict node labels in a newly formed target network. While existing transfer learning research has primarily focused on vector-based data, in which…

The ability to train complex and highly effective models often requires an abundance of training data, which can easily become a bottleneck in cost, time, and computational resources. Batch active learning, which adaptively issues batched…

Neural machine translation is known to require large numbers of parallel training sentences, which generally prevent it from excelling on low-resource language pairs. This thesis explores the use of cross-lingual transfer learning on neural…

Given a set of heterogeneous source datasets with their classifiers, how can we quickly find the most useful source dataset for a specific target task? We address the problem of measuring transferability between source and target datasets,…

Transfer learning has been successfully applied across many high-impact applications. However, most existing work focuses on the static transfer learning setting, and very little is devoted to modeling the time evolving target domain, such…

Transfer learning is crucial in training deep neural networks on new target tasks. Current transfer learning methods always assume at least one of (i) source and target task label spaces overlap, (ii) source datasets are available, and…

Training relational foundation models requires learning representations that transfer across tasks, yet available supervision is typically limited to a small number of prediction targets per database. This task scarcity causes learned…

In multi-label classification, an instance may be associated with a set of labels simultaneously. Recently, the research on multi-label classification has largely shifted its focus to the other end of the spectrum where the number of labels…

In cross-lingual transfer, NLP models over one or more source languages are applied to a low-resource target language. While most prior work has used a single source model or a few carefully selected models, here we consider a `massive'…

Adversarial learning has been successfully embedded into deep networks to learn transferable features, which reduce distribution discrepancy between the source and target domains. Existing domain adversarial networks assume fully shared…

Classical Domain Adaptation methods acquire transferability by regularizing the overall distributional discrepancies between features in the source domain (labeled) and features in the target domain (unlabeled). They often do not…

Recent deep learning-based methods outperform traditional learning methods on remote sensing (RS) semantic segmentation/classification tasks. However, they require large training datasets and are generally known for lack of transferability…