Related papers: Budget-Aware Adapters for Multi-Domain Learning

Neural networks (NNs) achieve outstanding performance in many domains; however, their decision processes are often opaque and their inference can be computationally expensive in resource-constrained environments. We recently proposed…

Beam selection for millimeter-wave links in a vehicular scenario is a challenging problem, as an exhaustive search among all candidate beam pairs cannot be assuredly completed within short contact times. We solve this problem via a novel…

Deep learning (DL) models have achieved great success in many application domains. As such, many industrial companies such as Google and Facebook have acknowledged the importance of multi-tenant DL services. Although the multi-tenant…

Domain adaptation is the supervised learning setting in which the training and test data are sampled from different distributions: training data is sampled from a source domain, whilst test data is sampled from a target domain. This paper…

The insertion of deep learning in medical image analysis had lead to the development of state-of-the art strategies in several applications such a disease classification, as well as abnormality detection and segmentation. However, even the…

In this paper, we introduce a discrete variant of the meta-learning framework. Meta-learning aims at exploiting prior experience and data to improve performance on future tasks. By now, there exist numerous formulations for meta-learning in…

In this work, we present a new, algorithm for multi-domain learning. Given a pretrained architecture and a set of visual domains received sequentially, the goal of multi-domain learning is to produce a single model performing a task in all…

Data sparsity and cold-start problems are persistent challenges in recommendation systems. Cross-domain recommendation (CDR) is a promising solution that utilizes knowledge from the source domain to improve the recommendation performance in…

We propose Impatient Deep Neural Networks (DNNs) which deal with dynamic time budgets during application. They allow for individual budgets given a priori for each test example and for anytime prediction, i.e., a possible interruption at…

Unsupervised domain adaptation (UDA) with pre-trained language models (PrLM) has achieved promising results since these pre-trained models embed generic knowledge learned from various domains. However, fine-tuning all the parameters of the…

We propose to focus on the problem of discovering neural network architectures efficient in terms of both prediction quality and cost. For instance, our approach is able to solve the following tasks: learn a neural network able to predict…

Machine Learning (ML) models are very effective in many learning tasks, due to the capability to extract meaningful information from large data sets. Nevertheless, there are learning problems that cannot be easily solved relying on pure…

Universal domain adaptation (UniDA) is a practical but challenging problem, in which information about the relation between the source and the target domains is not given for knowledge transfer. Existing UniDA methods may suffer from the…

Recent advancements in deep neural networks have markedly enhanced the performance of computer vision tasks, yet the specialized nature of these networks often necessitates extensive data and high computational power. Addressing these…

Recently unsupervised domain adaptation for the semantic segmentation task has become more and more popular due to high-cost of pixel-level annotation on real-world images. However, most domain adaptation methods are only restricted to…

Classification and identification of the materials lying over or beneath the Earth's surface have long been a fundamental but challenging research topic in geoscience and remote sensing (RS) and have garnered a growing concern owing to the…

Model-agnostic meta-learners aim to acquire meta-learned parameters from similar tasks to adapt to novel tasks from the same distribution with few gradient updates. With the flexibility in the choice of models, those frameworks demonstrate…

Most domain adaptation methods focus on single-source-single-target adaptation settings. Multi-target domain adaptation is a powerful extension in which a single classifier is learned for multiple unlabeled target domains. To build a…

Many software systems today face uncertain operating conditions, such as sudden changes in the availability of resources or unexpected user behavior. Without proper mitigation these uncertainties can jeopardize the system goals.…

Large language models (LLMs) often suffer from catastrophic forgetting in continual learning (CL) scenarios, where performance on previously learned tasks degrades severely while training on sequentially arriving tasks. Although pioneering…