NeuroTrails: Training with Dynamic Sparse Heads as the Key to Effective Ensembling

• URL: http://arxiv.org/abs/2505.17909v1
• Date: Fri, 23 May 2025 13:53:21 GMT
• Title: NeuroTrails: Training with Dynamic Sparse Heads as the Key to Effective Ensembling
• Authors: Bram Grooten, Farid Hasanov, Chenxiang Zhang, Qiao Xiao, Boqian Wu, Zahra Atashgahi, Ghada Sokar, Shiwei Liu, Lu Yin, Elena Mocanu, Mykola Pechenizkiy, Decebal Constantin Mocanu,
• Abstract summary: We introduce $textbfNeuroTrails$, a sparse multi-head architecture with dynamically evolving topology.<n>NeuroTrails displays efficacy with convolutional and transformer-based architectures on computer vision and language tasks.
• Score: 35.837527844931266
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Model ensembles have long been a cornerstone for improving generalization and robustness in deep learning. However, their effectiveness often comes at the cost of substantial computational overhead. To address this issue, state-of-the-art methods aim to replicate ensemble-class performance without requiring multiple independently trained networks. Unfortunately, these algorithms often still demand considerable compute at inference. In response to these limitations, we introduce $\textbf{NeuroTrails}$, a sparse multi-head architecture with dynamically evolving topology. This unexplored model-agnostic training paradigm improves ensemble performance while reducing the required resources. We analyze the underlying reason for its effectiveness and observe that the various neural trails induced by dynamic sparsity attain a $\textit{Goldilocks zone}$ of prediction diversity. NeuroTrails displays efficacy with convolutional and transformer-based architectures on computer vision and language tasks. Experiments on ResNet-50/ImageNet, LLaMA-350M/C4, among many others, demonstrate increased accuracy and stronger robustness in zero-shot generalization, while requiring significantly fewer parameters.

Related papers

• A Comprehensively Adaptive Architectural Optimization-Ingrained Quantum Neural Network Model for Cloud Workloads Prediction [4.501295034557007]
  This work proposes a novel Comprehensively Adaptive Architectural Optimization-based Variable Quantum Neural Network (CA-QNN)<n>The model converts workload data into qubits, processed through qubit neurons with Controlled NOT-gated activation functions for intuitive pattern recognition.<n>The proposed model demonstrates superior prediction accuracy, reducing prediction errors by up to 93.40% and 91.27% compared to existing deep learning and QNN-based approaches.
  arXiv  Detail & Related papers  (2025-07-11T05:07:21Z)
• Global Convergence and Rich Feature Learning in $L$-Layer Infinite-Width Neural Networks under $μ$P Parametrization [66.03821840425539]
  In this paper, we investigate the training dynamics of $L$-layer neural networks using the tensor gradient program (SGD) framework.<n>We show that SGD enables these networks to learn linearly independent features that substantially deviate from their initial values.<n>This rich feature space captures relevant data information and ensures that any convergent point of the training process is a global minimum.
  arXiv  Detail & Related papers  (2025-03-12T17:33:13Z)
• NeuroPrune: A Neuro-inspired Topological Sparse Training Algorithm for Large Language Models [35.10729451729596]
  Transformer-based Language Models have become ubiquitous in Natural Language Processing (NLP) However, expensive training as well as inference remains a significant impediment to their widespread applicability. Inspired by brain neuronal networks, we explore sparsity approaches through the lens of network topology.
  arXiv  Detail & Related papers  (2024-02-28T22:21:47Z)
• Model-Based Control with Sparse Neural Dynamics [23.961218902837807]
  We propose a new framework for integrated model learning and predictive control. We show that our framework can deliver better closed-loop performance than existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-12-20T06:25:02Z)
• Activity Sparsity Complements Weight Sparsity for Efficient RNN Inference [2.5148788595166205]
  We show that activity sparsity can compose multiplicatively with parameter sparsity in a recurrent neural network model.<n>We achieve up to $20times$ reduction of computation while maintaining perplexities below $60$ on the Penn Treebank language modeling task.
  arXiv  Detail & Related papers  (2023-11-13T08:18:44Z)
• Efficient and Flexible Neural Network Training through Layer-wise Feedback Propagation [49.44309457870649]
  Layer-wise Feedback feedback (LFP) is a novel training principle for neural network-like predictors.<n>LFP decomposes a reward to individual neurons based on their respective contributions.<n>Our method then implements a greedy reinforcing approach helpful parts of the network and weakening harmful ones.
  arXiv  Detail & Related papers  (2023-08-23T10:48:28Z)
• Solving Large-scale Spatial Problems with Convolutional Neural Networks [88.31876586547848]
  We employ transfer learning to improve training efficiency for large-scale spatial problems. We propose that a convolutional neural network (CNN) can be trained on small windows of signals, but evaluated on arbitrarily large signals with little to no performance degradation.
  arXiv  Detail & Related papers  (2023-06-14T01:24:42Z)
• Powerpropagation: A sparsity inducing weight reparameterisation [65.85142037667065]
  We introduce Powerpropagation, a new weight- parameterisation for neural networks that leads to inherently sparse models. Models trained in this manner exhibit similar performance, but have a distribution with markedly higher density at zero, allowing more parameters to be pruned safely. Here, we combine Powerpropagation with a traditional weight-pruning technique as well as recent state-of-the-art sparse-to-sparse algorithms, showing superior performance on the ImageNet benchmark.
  arXiv  Detail & Related papers  (2021-10-01T10:03:57Z)
• Dynamic Neural Diversification: Path to Computationally Sustainable Neural Networks [68.8204255655161]
  Small neural networks with a constrained number of trainable parameters, can be suitable resource-efficient candidates for many simple tasks. We explore the diversity of the neurons within the hidden layer during the learning process. We analyze how the diversity of the neurons affects predictions of the model.
  arXiv  Detail & Related papers  (2021-09-20T15:12:16Z)
• Efficient Model-Based Multi-Agent Mean-Field Reinforcement Learning [89.31889875864599]
  We propose an efficient model-based reinforcement learning algorithm for learning in multi-agent systems. Our main theoretical contributions are the first general regret bounds for model-based reinforcement learning for MFC. We provide a practical parametrization of the core optimization problem.
  arXiv  Detail & Related papers  (2021-07-08T18:01:02Z)
• Gone Fishing: Neural Active Learning with Fisher Embeddings [55.08537975896764]
  There is an increasing need for active learning algorithms that are compatible with deep neural networks. This article introduces BAIT, a practical representation of tractable, and high-performing active learning algorithm for neural networks.
  arXiv  Detail & Related papers  (2021-06-17T17:26:31Z)
• The Untapped Potential of Off-the-Shelf Convolutional Neural Networks [29.205446247063673]
  We show that existing off-the-shelf models like ResNet-50 are capable of over 95% accuracy on ImageNet. This level of performance currently exceeds that of models with over 20x more parameters and significantly more complex training procedures.
  arXiv  Detail & Related papers  (2021-03-17T20:04:46Z)
• A Simple Fine-tuning Is All You Need: Towards Robust Deep Learning Via Adversarial Fine-tuning [90.44219200633286]
  We propose a simple yet very effective adversarial fine-tuning approach based on a $textitslow start, fast decay$ learning rate scheduling strategy. Experimental results show that the proposed adversarial fine-tuning approach outperforms the state-of-the-art methods on CIFAR-10, CIFAR-100 and ImageNet datasets.
  arXiv  Detail & Related papers  (2020-12-25T20:50:15Z)
• Computation on Sparse Neural Networks: an Inspiration for Future Hardware [20.131626638342706]
  We describe the current status of the research on the computation of sparse neural networks. We discuss the model accuracy influenced by the number of weight parameters and the structure of the model. We show that for practically complicated problems, it is more beneficial to search large and sparse models in the weight dominated region.
  arXiv  Detail & Related papers  (2020-04-24T19:13:50Z)

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.