Related papers: SMART: A Spectral Transfer Approach to Multi-Task …

Intelligent spectrum management is crucial for improving spectrum efficiency and achieving secure utilization of spectrum resources. However, existing intelligent spectrum management methods, typically based on small-scale models, suffer…

A typical assumption in supervised machine learning is that the train (source) and test (target) datasets follow completely the same distribution. This assumption is, however, often violated in uncertain real-world applications, which…

Multimodal retrieval relies heavily on single-vector retrievers, which compress rich, sequential token sequences into one single global representation. While efficient, they discard fine-grained, local evidence critical for dense retrieval…

Automatic Music Transcription (AMT), inferring musical notes from raw audio, is a challenging task at the core of music understanding. Unlike Automatic Speech Recognition (ASR), which typically focuses on the words of a single speaker, AMT…

Transfer learning on tabular data is challenging due to disparate feature spaces across domains, in contrast to the homogeneous structures of image and text. Large language models (LLMs) offer a knowledge base to improve the limited…

Many real-world large-scale regression problems can be formulated as Multi-task Learning (MTL) problems with a massive number of tasks, as in retail and transportation domains. However, existing MTL methods still fail to offer both the…

Meta-learning aims to learn general knowledge with diverse training tasks conducted from limited data, and then transfer it to new tasks. It is commonly believed that increasing task diversity will enhance the generalization ability of…

Precision matrix estimation is essential in various fields; yet it is challenging when samples for the target study are limited. Transfer learning can enhance estimation accuracy by leveraging data from related source studies. We propose…

Multi Task Learning (MTL) efficiently leverages useful information contained in multiple related tasks to help improve the generalization performance of all tasks. This article conducts a large dimensional analysis of a simple but, as we…

Transferring representation for multitask imitation learning has the potential to provide improved sample efficiency on learning new tasks, when compared to learning from scratch. In this work, we provide a statistical guarantee indicating…

Distance metric learning (DML) is a critical factor for image analysis and pattern recognition. To learn a robust distance metric for a target task, we need abundant side information (i.e., the similarity/dissimilarity pairwise constraints…

Adaptive interventions (AIs) are increasingly becoming popular in medical and behavioral sciences. An AI is a sequence of individualized intervention options that specify for whom and under what conditions different intervention options…

Transfer learning, which allows a source task to affect the inductive bias of the target task, is widely used in computer vision. The typical way of conducting transfer learning with deep neural networks is to fine-tune a model pre-trained…

In recent years, transfer learning has garnered significant attention. Its ability to leverage knowledge from related studies to improve generalization performance in a target study has made it highly appealing. This paper focuses on…

Despite the remarkable success achieved by graph convolutional networks for functional brain activity analysis, the heterogeneity of functional patterns and the scarcity of imaging data still pose challenges in many tasks. Transferring…

Transfer learning allows practitioners to recognize and apply knowledge learned in previous tasks (source task) to new tasks or new domains (target task), which share some commonality. The two important factors impacting the performance of…

Training Deep Neural Networks (DNNs) is still highly time-consuming and compute-intensive. It has been shown that adapting a pretrained model may significantly accelerate this process. With a focus on classification, we show that current…

We observe that current state-of-the-art (SOTA) methods suffer from the performance imbalance issue when performing multi-task reinforcement learning (MTRL) tasks. While these methods may achieve impressive performance on average, they…

This paper studies the fast adaptive beamforming for the multiuser multiple-input single-output downlink. Existing deep learning-based approaches assume that training and testing channels follow the same distribution which causes task…

The multitask diffusion LMS is an efficient strategy to simultaneously infer, in a collaborative manner, multiple parameter vectors. Existing works on multitask problems assume that all agents respond to data synchronously. In several…