Related papers: BD-Merging: Bias-Aware Dynamic Model Merging with …

As machine learning becomes more prominent there is a growing demand to perform several inference tasks in parallel. Running a dedicated model for each task is computationally expensive and therefore there is a great interest in multi-task…

When faced with learning a set of inter-related tasks from a limited amount of usable data, learning each task independently may lead to poor generalization performance. Multi-Task Learning (MTL) exploits the latent relations between tasks…

Multilingual neural machine translation (MNMT) learns to translate multiple language pairs with a single model, potentially improving both the accuracy and the memory-efficiency of deployed models. However, the heavy data imbalance between…

Transfer learning - i.e., further fine-tuning a pre-trained model on a downstream task - can confer significant advantages, including improved downstream performance, faster convergence, and better sample efficiency. These advantages have…

Uncertainty-aware deep learning (DL) models recently gained attention in fault diagnosis as a way to promote the reliable detection of faults when out-of-distribution (OOD) data arise from unseen faults (epistemic uncertainty) or the…

Energy-Based Models (EBMs) have been widely used for generative modeling. Contrastive Divergence (CD), a prevailing training objective for EBMs, requires sampling from the EBM with Markov Chain Monte Carlo methods (MCMCs), which leads to an…

Recent advances in decentralized deep learning algorithms have demonstrated cutting-edge performance on various tasks with large pre-trained models. However, a pivotal prerequisite for achieving this level of competitiveness is the…

Recent advances in diffusion models have demonstrated their strong capabilities in generating high-fidelity samples from complex distributions through an iterative refinement process. Despite the empirical success of diffusion models in…

This paper presents a novel method that allows a machine learning algorithm following the transformation-based learning paradigm \cite{brill95:tagging} to be applied to multiple classification tasks by training jointly and simultaneously on…

Edge computing has emerged as an alternative to reduce transmission and processing delay and preserve privacy of the video streams. However, the ever-increasing complexity of Deep Neural Networks (DNNs) used in video-based applications…

Model merging aims to integrate multiple task-specific fine-tuned models derived from a shared pre-trained checkpoint into a single multi-task model without additional training. Despite extensive research, task interference remains a major…

In the era of large-scale training, model merging has evolved into a tool for creating multitasking models efficiently. It enables the knowledge of models to be fused, without the need for heavy computation as required in traditional…

Predicting whether a molecule can cross the blood-brain barrier (BBB) is a key step in early-stage neuro-pharmaceutical design, directly influencing the efficiency and success rate of drug development. Traditional methods based on…

Weak-strong consistency learning strategies are widely employed in semi-supervised medical image segmentation to train models by leveraging limited labeled data and enforcing weak-to-strong consistency. However, existing methods primarily…

Model merging combines the parameters of multiple neural networks into a single model without additional training. As fine-tuned large language models (LLMs) proliferate, merging offers a computationally efficient alternative to ensembles…

Recently,the detection transformer has gained substantial attention for its inherent minimal post-processing requirement.However,this paradigm relies on abundant training data,yet in the context of the cross-domain adaptation,insufficient…

Federated learning is a promising distributed machine learning paradigm that can effectively exploit large-scale data without exposing users' privacy. However, it may incur significant communication overhead, thereby potentially impairing…

Meta-learning offers a principled framework leveraging \emph{task-invariant} priors from related tasks, with which \emph{task-specific} models can be fine-tuned on downstream tasks, even with limited data records. Gradient-based…

Meta-learning methods perform well on new within-distribution tasks but often fail when adapting to out-of-distribution target tasks, where transfer from source tasks can induce negative transfer. We propose a causally-aware Bayesian…

Deterministic mathematical models, such as those specified via differential equations, are a powerful tool to communicate scientific insight. However, such models are necessarily simplified descriptions of the real world. Generalised…