相关论文: Guided Transfer Learning

Transfer-learning and meta-learning are two effective methods to apply knowledge learned from large data sources to new tasks. In few-class, few-shot target task settings (i.e. when there are only a few classes and training examples…

Not all learnable parameters (e.g., weights) contribute equally to a neural network's decision function. In fact, entire layers' parameters can sometimes be reset to random values with little to no impact on the model's decisions. We…

Fine-tuning of self-supervised models is a powerful transfer learning method in a variety of fields, including speech processing, since it can utilize generic feature representations obtained from large amounts of unlabeled data.…

Federated Learning offers a way to train deep neural networks in a distributed fashion. While this addresses limitations related to distributed data, it incurs a communication overhead as the model parameters or gradients need to be…

Fine-tuning pre-trained generative language models to down-stream language generation tasks has shown promising results. However, this comes with the cost of having a single, large model for each task, which is not ideal in low-memory/power…

Federated learning enables many applications benefiting distributed and private datasets of a large number of potential data-holding clients. However, different clients usually have their own particular objectives in terms of the tasks to…

In recent years, deep neural networks have known a wide success in various application domains. However, they require important computational and memory resources, which severely hinders their deployment, notably on mobile devices or for…

We propose a method to transfer knowledge across neural machine translation (NMT) models by means of a shared dynamic vocabulary. Our approach allows to extend an initial model for a given language pair to cover new languages by adapting…

Determining onflow parameters is crucial from the perspectives of wind tunnel testing and regular flight and wind turbine operations. These parameters have traditionally been predicted via direct measurements which might lead to challenges…

Deep learning models have been widely used during the last decade due to their outstanding learning and abstraction capacities. However, one of the main challenges any scientist has to face using deep learning models is to establish the…

In this paper, we propose a machine learning model, which dynamically changes the features during training. Our main motivation is to update the model in a small content during the training process with replacing less descriptive features…

Deep learning models are yielding increasingly better performances thanks to multiple factors. To be successful, model may have large number of parameters or complex architectures and be trained on large dataset. This leads to large…

In transfer learning, we wish to make inference about a target population when we have access to data both from the distribution itself, and from a different but related source distribution. We introduce a flexible framework for transfer…

This work offers a heuristic evaluation of the effects of variations in machine learning training regimes and learning paradigms on the energy consumption of computing, especially HPC hardware with a life-cycle aware perspective. While…

The goal of Deep Domain Adaptation is to make it possible to use Deep Nets trained in one domain where there is enough annotated training data in another where there is little or none. Most current approaches have focused on learning…

It has been demonstrated that deep neural networks outperform traditional machine learning. However, deep networks lack generalisability, that is, they will not perform as good as in a new (testing) set drawn from a different distribution…

Knowledge transfer between heterogeneous source and target networks and tasks has received a lot of attention in recent times as large amounts of quality labeled data can be difficult to obtain in many applications. Existing approaches…

Recent works on parameter-efficient transfer learning (PETL) show the potential to adapt a pre-trained Vision Transformer to downstream recognition tasks with only a few learnable parameters. However, since they usually insert new…

As an integral part of contemporary manufacturing, monitoring systems obtain valuable information during machining to oversee the condition of both the process and the machine. Recently, diverse algorithms have been employed to detect tool…

Modern software systems are built to be used in dynamic environments using configuration capabilities to adapt to changes and external uncertainties. In a self-adaptation context, we are often interested in reasoning about the performance…