Related papers: Foldable SuperNets: Scalable Merging of Transforme…
We propose a novel method to merge convolutional neural-nets for the inference stage. Given two well-trained networks that may have different architectures that handle different tasks, our method aligns the layers of the original networks…
Model merging has gained prominence in machine learning as a method to integrate multiple trained models into a single model without accessing the original training data. While existing approaches have demonstrated success in domains such…
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…
Fine-tuning pre-trained language models has become the prevalent paradigm for building downstream NLP models. Oftentimes fine-tuned models are readily available but their training data is not, due to data privacy or intellectual property…
Distributed learning frameworks often rely on exchanging model parameters across workers, instead of revealing their raw data. A prime example is federated learning that exchanges the gradients or weights of each neural network model. Under…
Large machine learning models trained on diverse data have recently seen unprecedented success. Federated learning enables training on private data that may otherwise be inaccessible, such as domain-specific datasets decentralized across…
Although multi-task learning is widely applied in intelligent services, traditional multi-task modeling methods often require customized designs based on specific task combinations, resulting in a cumbersome modeling process. Inspired by…
Modern deep learning usually treats models as separate artifacts: trained independently, specialized for particular purposes, and replaced when improved versions appear. This thesis studies model merging as an alternative paradigm:…
We propose a simple scheme for merging two neural networks trained with different starting initialization into a single one with the same size as the original ones. We do this by carefully selecting channels from each input network. Our…
We introduce model folding, a novel data-free model compression technique that merges structurally similar neurons across layers, significantly reducing the model size without the need for fine-tuning or access to training data. Unlike…
Model merging has emerged as an efficient method to combine multiple single-task fine-tuned models. The merged model can enjoy multi-task capabilities without expensive training. While promising, merging into a single model often suffers…
Fine-tuning pre-trained models provides significant advantages in downstream performance. The ubiquitous nature of pre-trained models such as BERT and its derivatives in natural language processing has also led to a proliferation of…
Recently, innovative model aggregation methods based on knowledge distillation (KD) have been proposed for federated learning (FL). These methods not only improved the robustness of model aggregation over heterogeneous learning environment,…
Training mixed-domain translation models is a complex task that demands tailored architectures and costly data preparation techniques. In this work, we leverage federated learning (FL) in order to tackle the problem. Our investigation…
Federated Learning (FL) seeks to train a model collaboratively without sharing private training data from individual clients. Despite its promise, FL encounters challenges such as high communication costs for large-scale models and the…
Federated learning (FL) enables distribution of machine learning workloads from the cloud to resource-limited edge devices. Unfortunately, current deep networks remain not only too compute-heavy for inference and training on edge devices,…
Deep Neural Network (DNN) models are usually trained sequentially from one layer to another, which causes forward, backward and update locking's problems, leading to poor performance in terms of training time. The existing parallel…
Federated Learning (FL) enables the training of Deep Learning models without centrally collecting possibly sensitive raw data. The most used algorithms for FL are parameter-averaging based schemes (e.g., Federated Averaging) that, however,…
Federated learning is used for decentralized training of machine learning models on a large number (millions) of edge mobile devices. It is challenging because mobile devices often have limited communication bandwidth and local computation…
Merging multiple expert models offers a promising approach for performing multi-task learning without accessing their original data. Existing methods attempt to alleviate task conflicts by sparsifying task vectors or promoting orthogonality…