paper-with-me

Papers

Subspace Node Pruning

2024-05-26 · Joshua Offergeld, Marcel van Gerven, Nasir Ahmad

Efficiency of neural network inference is undeniably important in a time where commercial use of AI models increases daily. Node pruning is the art of removing computational units such as neurons, filters, attention heads, or even entire layers to significantly reduce inference time while retaining network performance. In this work, we propose the projection of unit activations to an orthogonal subspace in which there is no redundant activity and within which we may prune nodes while simultaneously recovering the impact of lost units via linear least squares. We identify that, for effective node pruning, this subspace must be constructed using a triangular transformation matrix, a transformation which is equivalent to and unnormalized Gram-Schmidt orthogonalization. We furthermore show that the order in which units are orthogonalized can be optimised to maximally reduce node activations in our subspace and thereby form a more optimal ranking of nodes. Finally, we leverage these orthogonal subspaces to automatically determine layer-wise pruning ratios based upon the relative scale of node activations in our subspace, equivalent to cumulative variance. Our proposed method reaches state of the art when pruning ImageNet trained VGG-16 and rivals more complex state of the art methods when pruning ResNet-50 networks across a range of pruning ratios.

📄 PDF Abstract BibTeX arXiv:2405.17506

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

VGG-16 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Pruning 설명 없음

Similar Papers 제목 키워드 기반

Koopman Subspace Pruning in Reproducing Kernel Hilbert Spaces via Principal Vectors

2026-04-01 · Dhruv Shah, Jorge Cortes arxiv

Data-driven approximations of the infinite-dimensional Koopman operator rely on finite-dimensional projections, where the predictive accuracy of the resulting models hinges heavily on the invariance of the chosen subspac…

Cut-ViT: Task-Specific Model Pruning via Gram Anchoring Subspace Consistency

2026-08-28 · Jianjian Yin, Liulei Li, Tao Chen, Yi Chen 외 arxiv

Pruning visual foundation models has attracted considerable attention. However, existing methods focus on rigid point-to-point token alignment on a single dataset for pruning, suffering from two limitations: i) robustnes…

Diversity Based Edge Pruning of Neural Networks Using Determinantal Point Processes

2021-03-04 · ICLR Workshop Neural_Compression 2021 5 · Rupam Acharyya, Boyu Zhang, Ankani Chattoraj, Shouman Das 외

Deep learning architectures with huge number of parameters are often compressed using pruning techniques. Two classes of pruning techniques are node pruning and edge pruning. A fairly recent work established that Determi…

DiversityPoint Processes

Lockdown: Backdoor Defense for Federated Learning with Isolated Subspace Training

2023-09-21

Federated learning (FL) is vulnerable to backdoor attacks due to its distributed computing nature. Existing defense solution usually requires larger amount of computation in either the training or testing phase, which l…

backdoor defenseDistributed ComputingFederated Learning

Lockdown: Backdoor Defense for Federated Learning with Isolated Subspace Training

2023-09-21 · NeurIPS 2023 11

Federated learning (FL) is vulnerable to backdoor attacks due to its distributed computing nature. Existing defense solution usually requires larger amount of computation in either the training or testing phase, which l…

backdoor defenseDistributed ComputingFederated Learning