相关论文: Multi-Task Zipping via Layer-wise Neuron Sharing

Multi-task learning leverages potential correlations among related tasks to extract common features and yield performance gains. However, most previous works only consider simple or weak interactions, thereby failing to model complex…

Model merging is an effective strategy to merge multiple models for enhancing model performances, and more efficient than ensemble learning as it will not introduce extra computation into inference. However, limited research explores if the…

Multi-task learning is commonly used in autonomous driving for solving various visual perception tasks. It offers significant benefits in terms of both performance and computational complexity. Current work on multi-task learning networks…

Deep learning-based Magnetic Resonance (MR) reconstruction methods have focused on generating high-quality images but often overlook the impact on downstream tasks (e.g., segmentation) that utilize the reconstructed images. Cascading…

Deep neural networks trained for predicting cellular events from DNA sequence have become emerging tools to help elucidate the biological mechanism underlying the associations identified in genome-wide association studies. To enhance the…

Transfer learning has become a powerful tool to initialize deep learning models to achieve faster convergence and higher performance. This is especially useful in the medical imaging analysis domain, where data scarcity limits possible…

A rising research challenge is running costly machine learning (ML) networks locally on resource-constrained edge devices. ML networks with large convolutional layers can easily exceed available memory, increasing latency due to excessive…

Neural network based methods have obtained great progress on a variety of natural language processing tasks. However, in most previous works, the models are learned based on single-task supervised objectives, which often suffer from…

Multi-task learning has the potential to improve generalization by maximizing positive transfer between tasks while reducing task interference. Fully achieving this potential is hindered by manually designed architectures that remain static…

This work identifies a simple pre-training mechanism that leads to representations exhibiting better continual and transfer learning. This mechanism -- the repeated resetting of weights in the last layer, which we nickname "zapping" -- was…

Multi-task learning (MTL) trains deep neural networks to optimize several objectives simultaneously using a shared backbone, which leads to reduced computational costs, improved data efficiency, and enhanced performance through cross-task…

Recent methods aim to merge neural networks (NNs) with identical architectures trained on different tasks into a single multi-task model. While most works focus on the simpler setup of merging NNs initialized from a common pre-trained…

Most contemporary multi-task learning methods assume linear models. This setting is considered shallow in the era of deep learning. In this paper, we present a new deep multi-task representation learning framework that learns cross-task…

Deep networks consume a large amount of memory by their nature. A natural question arises can we reduce that memory requirement whilst maintaining performance. In particular, in this work we address the problem of memory efficient learning…

Multi-task learning (MTL) paradigm focuses on jointly learning two or more tasks, aiming for significant improvement w.r.t model's generalizability, performance, and training/inference memory footprint. The aforementioned benefits become…

Most uses of machine learning today involve training a model from scratch for a particular task, or sometimes starting with a model pretrained on a related task and then fine-tuning on a downstream task. Both approaches offer limited…

Neural networks provide a powerful tool for applications from classification and regression to general purpose alternative computing. Photonics have the potential to provide enormous speed benefits over electronic and software networks,…

In this paper, we present a novel data-free method for merging neural networks in weight space. Differently from most existing works, our method optimizes for the permutations of network neurons globally across all layers. This allows us to…

Heterogeneous multi-task learning (HMTL) is an important topic in multi-task learning (MTL). Most existing HMTL methods usually solve either scenario where all tasks reside in the same input (feature) space yet unnecessarily the consistent…

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…