Stitching for Neuroevolution: Recombining Deep Neural Networks without Breaking Them
- URL: http://arxiv.org/abs/2403.14224v1
- Date: Thu, 21 Mar 2024 08:30:44 GMT
- Title: Stitching for Neuroevolution: Recombining Deep Neural Networks without Breaking Them
- Authors: Arthur Guijt, Dirk Thierens, Tanja Alderliesten, Peter A. N. Bosman,
- Abstract summary: Traditional approaches to neuroevolution often start from scratch.
Recombining trained networks is non-trivial because architectures and feature representations typically differ.
We employ stitching, which merges the networks by introducing new layers at crossover points.
- Score: 0.0
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Traditional approaches to neuroevolution often start from scratch. This becomes prohibitively expensive in terms of computational and data requirements when targeting modern, deep neural networks. Using a warm start could be highly advantageous, e.g., using previously trained networks, potentially from different sources. This moreover enables leveraging the benefits of transfer learning (in particular vastly reduced training effort). However, recombining trained networks is non-trivial because architectures and feature representations typically differ. Consequently, a straightforward exchange of layers tends to lead to a performance breakdown. We overcome this by matching the layers of parent networks based on their connectivity, identifying potential crossover points. To correct for differing feature representations between these layers we employ stitching, which merges the networks by introducing new layers at crossover points. To train the merged network, only stitching layers need to be considered. New networks can then be created by selecting a subnetwork by choosing which stitching layers to (not) use. Assessing their performance is efficient as only their evaluation on data is required. We experimentally show that our approach enables finding networks that represent novel trade-offs between performance and computational cost, with some even dominating the original networks.
Related papers
- Sensitivity-Based Layer Insertion for Residual and Feedforward Neural
Networks [0.3831327965422187]
Training of neural networks requires tedious and often manual tuning of the network architecture.
We propose a systematic method to insert new layers during the training process, which eliminates the need to choose a fixed network size before training.
arXiv Detail & Related papers (2023-11-27T16:44:13Z) - Improving the Trainability of Deep Neural Networks through Layerwise
Batch-Entropy Regularization [1.3999481573773072]
We introduce and evaluate the batch-entropy which quantifies the flow of information through each layer of a neural network.
We show that we can train a "vanilla" fully connected network and convolutional neural network with 500 layers by simply adding the batch-entropy regularization term to the loss function.
arXiv Detail & Related papers (2022-08-01T20:31:58Z) - Increasing Depth of Neural Networks for Life-long Learning [2.0305676256390934]
We propose a novel method for continual learning based on the increasing depth of neural networks.
This work explores whether extending neural network depth may be beneficial in a life-long learning setting.
arXiv Detail & Related papers (2022-02-22T11:21:41Z) - Firefly Neural Architecture Descent: a General Approach for Growing
Neural Networks [50.684661759340145]
Firefly neural architecture descent is a general framework for progressively and dynamically growing neural networks.
We show that firefly descent can flexibly grow networks both wider and deeper, and can be applied to learn accurate but resource-efficient neural architectures.
In particular, it learns networks that are smaller in size but have higher average accuracy than those learned by the state-of-the-art methods.
arXiv Detail & Related papers (2021-02-17T04:47:18Z) - Dynamic Graph: Learning Instance-aware Connectivity for Neural Networks [78.65792427542672]
Dynamic Graph Network (DG-Net) is a complete directed acyclic graph, where the nodes represent convolutional blocks and the edges represent connection paths.
Instead of using the same path of the network, DG-Net aggregates features dynamically in each node, which allows the network to have more representation ability.
arXiv Detail & Related papers (2020-10-02T16:50:26Z) - Learning Connectivity of Neural Networks from a Topological Perspective [80.35103711638548]
We propose a topological perspective to represent a network into a complete graph for analysis.
By assigning learnable parameters to the edges which reflect the magnitude of connections, the learning process can be performed in a differentiable manner.
This learning process is compatible with existing networks and owns adaptability to larger search spaces and different tasks.
arXiv Detail & Related papers (2020-08-19T04:53:31Z) - Finding trainable sparse networks through Neural Tangent Transfer [16.092248433189816]
In deep learning, trainable sparse networks that perform well on a specific task are usually constructed using label-dependent pruning criteria.
In this article, we introduce Neural Tangent Transfer, a method that instead finds trainable sparse networks in a label-free manner.
arXiv Detail & Related papers (2020-06-15T08:58:01Z) - Compact Neural Representation Using Attentive Network Pruning [1.0152838128195465]
We describe a Top-Down attention mechanism that is added to a Bottom-Up feedforward network to select important connections and subsequently prune redundant ones at all parametric layers.
Our method not only introduces a novel hierarchical selection mechanism as the basis of pruning but also remains competitive with previous baseline methods in the experimental evaluation.
arXiv Detail & Related papers (2020-05-10T03:20:01Z) - Network Adjustment: Channel Search Guided by FLOPs Utilization Ratio [101.84651388520584]
This paper presents a new framework named network adjustment, which considers network accuracy as a function of FLOPs.
Experiments on standard image classification datasets and a wide range of base networks demonstrate the effectiveness of our approach.
arXiv Detail & Related papers (2020-04-06T15:51:00Z) - Semantic Drift Compensation for Class-Incremental Learning [48.749630494026086]
Class-incremental learning of deep networks sequentially increases the number of classes to be classified.
We propose a new method to estimate the drift, called semantic drift, of features and compensate for it without the need of any exemplars.
arXiv Detail & Related papers (2020-04-01T13:31:19Z) - Side-Tuning: A Baseline for Network Adaptation via Additive Side
Networks [95.51368472949308]
Adaptation can be useful in cases when training data is scarce, or when one wishes to encode priors in the network.
In this paper, we propose a straightforward alternative: side-tuning.
arXiv Detail & Related papers (2019-12-31T18:52:32Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.