MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection

• URL: http://arxiv.org/abs/2505.11416v1
• Date: Fri, 16 May 2025 16:29:19 GMT
• Title: MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection
• Authors: Pouya Shaeri, Ariane Middel,
• Abstract summary: Matrix-Interpolated Dropout Layer (MID-L) dynamically selects and activates only the most informative neurons.<n>Experiments on six benchmarks, including MNIST, CIFAR-10, CIFAR-100, SVHN, UCI Adult, and IMDB, show that MID-L achieves up to average 55% reduction in active neurons.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Modern neural networks often activate all neurons for every input, leading to unnecessary computation and inefficiency. We introduce Matrix-Interpolated Dropout Layer (MID-L), a novel module that dynamically selects and activates only the most informative neurons by interpolating between two transformation paths via a learned, input-dependent gating vector. Unlike conventional dropout or static sparsity methods, MID-L employs a differentiable Top-k masking strategy, enabling per-input adaptive computation while maintaining end-to-end differentiability. MID-L is model-agnostic and integrates seamlessly into existing architectures. Extensive experiments on six benchmarks, including MNIST, CIFAR-10, CIFAR-100, SVHN, UCI Adult, and IMDB, show that MID-L achieves up to average 55\% reduction in active neurons, 1.7$\times$ FLOPs savings, and maintains or exceeds baseline accuracy. We further validate the informativeness and selectivity of the learned neurons via Sliced Mutual Information (SMI) and observe improved robustness under overfitting and noisy data conditions. Additionally, MID-L demonstrates favorable inference latency and memory usage profiles, making it suitable for both research exploration and deployment on compute-constrained systems. These results position MID-L as a general-purpose, plug-and-play dynamic computation layer, bridging the gap between dropout regularization and efficient inference.

Related papers

• Deep-Unrolling Multidimensional Harmonic Retrieval Algorithms on Neuromorphic Hardware [78.17783007774295]
  This paper explores the potential of conversion-based neuromorphic algorithms for highly accurate and energy-efficient single-snapshot multidimensional harmonic retrieval.<n>A novel method for converting the complex-valued convolutional layers and activations into spiking neural networks (SNNs) is developed.<n>The converted SNNs achieve almost five-fold power efficiency at moderate performance loss compared to the original CNNs.
  arXiv  Detail & Related papers  (2024-12-05T09:41:33Z)
• Effective Non-Random Extreme Learning Machine [0.0]
  This paper introduces a new and enhanced learning algorithm for regression tasks, the Effective Non-Random ELM (ENR-ELM) The proposed method incorporates concepts from signal processing, such as basis functions and projections, into the ELM framework. Experimental results on both synthetic and real datasets demonstrate that our method overcomes the problems of traditional ELM while maintaining comparable predictive performance.
  arXiv  Detail & Related papers  (2024-11-25T09:42:42Z)
• Heterogenous Memory Augmented Neural Networks [84.29338268789684]
  We introduce a novel heterogeneous memory augmentation approach for neural networks. By introducing learnable memory tokens with attention mechanism, we can effectively boost performance without huge computational overhead. We show our approach on various image and graph-based tasks under both in-distribution (ID) and out-of-distribution (OOD) conditions.
  arXiv  Detail & Related papers  (2023-10-17T01:05:28Z)
• A Multi-Head Ensemble Multi-Task Learning Approach for Dynamical Computation Offloading [62.34538208323411]
  We propose a multi-head ensemble multi-task learning (MEMTL) approach with a shared backbone and multiple prediction heads (PHs) MEMTL outperforms benchmark methods in both the inference accuracy and mean square error without requiring additional training data.
  arXiv  Detail & Related papers  (2023-09-02T11:01:16Z)
• Efficient and Flexible Neural Network Training through Layer-wise Feedback Propagation [49.44309457870649]
  We present Layer-wise Feedback Propagation (LFP), a novel training principle for neural network-like predictors.<n>LFP decomposes a reward to individual neurons based on their respective contributions to solving a given task.<n>Our method then implements a greedy approach reinforcing helpful parts of the network and weakening harmful ones.
  arXiv  Detail & Related papers  (2023-08-23T10:48:28Z)
• MISNN: Multiple Imputation via Semi-parametric Neural Networks [9.594714330925703]
  Multiple imputation (MI) has been widely applied to missing value problems in biomedical, social and econometric research. We propose MISNN, a novel and efficient algorithm that incorporates feature selection for MI.
  arXiv  Detail & Related papers  (2023-05-02T21:45:36Z)
• Bayesian Neural Network Language Modeling for Speech Recognition [59.681758762712754]
  State-of-the-art neural network language models (NNLMs) represented by long short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming highly complex. In this paper, an overarching full Bayesian learning framework is proposed to account for the underlying uncertainty in LSTM-RNN and Transformer LMs.
  arXiv  Detail & Related papers  (2022-08-28T17:50:19Z)
• A memory-efficient neural ODE framework based on high-level adjoint differentiation [4.063868707697316]
  We present a new neural ODE framework, PNODE, based on high-level discrete algorithmic differentiation. We show that PNODE achieves the highest memory efficiency when compared with other reverse-accurate methods.
  arXiv  Detail & Related papers  (2022-06-02T20:46:26Z)
• DEMAND: Deep Matrix Approximately NonlinearDecomposition to Identify Meta, Canonical, and Sub-Spatial Pattern of functional Magnetic Resonance Imaging in the Human Brain [8.93274096260726]
  We propose a novel deep nonlinear matrix factorization named Deep Approximately Decomposition (DEMAND) in this work to take advantage of the shallow linear model, e.g., Sparse Dictionary Learning (SDL) and Deep Neural Networks (DNNs) DEMAND can reveal the reproducible meta, canonical, and sub-spatial features of the human brain more efficiently than other peer methodologies.
  arXiv  Detail & Related papers  (2022-05-20T15:55:01Z)
• Optimization-driven Machine Learning for Intelligent Reflecting Surfaces Assisted Wireless Networks [82.33619654835348]
  Intelligent surface (IRS) has been employed to reshape the wireless channels by controlling individual scattering elements' phase shifts. Due to the large size of scattering elements, the passive beamforming is typically challenged by the high computational complexity. In this article, we focus on machine learning (ML) approaches for performance in IRS-assisted wireless networks.
  arXiv  Detail & Related papers  (2020-08-29T08:39:43Z)

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.