Subspace Node Pruning

• URL: http://arxiv.org/abs/2405.17506v2
• Date: Tue, 01 Oct 2024 18:07:37 GMT
• Title: Subspace Node Pruning
• Authors: Joshua Offergeld, Marcel van Gerven, Nasir Ahmad,
• Abstract summary: nodes 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. 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.
• Score: 2.3125457626961263
• License:
• Abstract: 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.

Related papers

• Sparse Decomposition of Graph Neural Networks [20.768412002413843]
  We propose an approach to reduce the number of nodes that are included during aggregation. We achieve this through a sparse decomposition, learning to approximate node representations using a weighted sum of linearly transformed features. We demonstrate via extensive experiments that our method outperforms other baselines designed for inference speedup.
  arXiv  Detail & Related papers  (2024-10-25T17:52:16Z)
• Re-visiting Skip-Gram Negative Sampling: Dimension Regularization for More Efficient Dissimilarity Preservation in Graph Embeddings [8.858596502294471]
  We show that node-wise repulsion is, in aggregate, an approximate re-centering of the node embedding dimensions. We propose an algorithm augmentation framework that speeds up any existing algorithm, supervised or unsupervised.
  arXiv  Detail & Related papers  (2024-04-30T19:43:01Z)
• Efficient Link Prediction via GNN Layers Induced by Negative Sampling [92.05291395292537]
  Graph neural networks (GNNs) for link prediction can loosely be divided into two broad categories. First, emphnode-wise architectures pre-compute individual embeddings for each node that are later combined by a simple decoder to make predictions. Second, emphedge-wise methods rely on the formation of edge-specific subgraph embeddings to enrich the representation of pair-wise relationships.
  arXiv  Detail & Related papers  (2023-10-14T07:02:54Z)
• Reinforcement Learning for Node Selection in Branch-and-Bound [52.2648997215667]
  Current state-of-the-art selectors utilize either hand-crafted ensembles that automatically switch between naive sub-node selectors, or learned node selectors that rely on individual node data. We propose a novel simulation technique that uses reinforcement learning (RL) while considering the entire tree state, rather than just isolated nodes.
  arXiv  Detail & Related papers  (2023-09-29T19:55:56Z)
• Globally Optimal Training of Neural Networks with Threshold Activation Functions [63.03759813952481]
  We study weight decay regularized training problems of deep neural networks with threshold activations. We derive a simplified convex optimization formulation when the dataset can be shattered at a certain layer of the network.
  arXiv  Detail & Related papers  (2023-03-06T18:59:13Z)
• Learning Smooth Neural Functions via Lipschitz Regularization [92.42667575719048]
  We introduce a novel regularization designed to encourage smooth latent spaces in neural fields. Compared with prior Lipschitz regularized networks, ours is computationally fast and can be implemented in four lines of code.
  arXiv  Detail & Related papers  (2022-02-16T21:24:54Z)
• Layer Adaptive Node Selection in Bayesian Neural Networks: Statistical Guarantees and Implementation Details [0.5156484100374059]
  Sparse deep neural networks have proven to be efficient for predictive model building in large-scale studies. We propose a Bayesian sparse solution using spike-and-slab Gaussian priors to allow for node selection during training. We establish the fundamental result of variational posterior consistency together with the characterization of prior parameters.
  arXiv  Detail & Related papers  (2021-08-25T00:48:07Z)
• Basis Scaling and Double Pruning for Efficient Inference in Network-Based Transfer Learning [1.3467579878240454]
  We decompose a convolutional layer into two layers: a convolutional layer with the orthonormal basis vectors as the filters, and a "BasisScalingConv" layer which is responsible for rescaling the features. We can achieve pruning ratios up to 74.6% for CIFAR-10 and 98.9% for MNIST in model parameters.
  arXiv  Detail & Related papers  (2021-08-06T00:04:02Z)
• Joint Multi-Dimension Pruning via Numerical Gradient Update [120.59697866489668]
  We present joint multi-dimension pruning (abbreviated as JointPruning), an effective method of pruning a network on three crucial aspects: spatial, depth and channel simultaneously. We show that our method is optimized collaboratively across the three dimensions in a single end-to-end training and it is more efficient than the previous exhaustive methods.
  arXiv  Detail & Related papers  (2020-05-18T17:57:09Z)
• Controllable Orthogonalization in Training DNNs [96.1365404059924]
  Orthogonality is widely used for training deep neural networks (DNNs) due to its ability to maintain all singular values of the Jacobian close to 1. This paper proposes a computationally efficient and numerically stable orthogonalization method using Newton's iteration (ONI) We show that our method improves the performance of image classification networks by effectively controlling the orthogonality to provide an optimal tradeoff between optimization benefits and representational capacity reduction. We also show that ONI stabilizes the training of generative adversarial networks (GANs) by maintaining the Lipschitz continuity of a network, similar to spectral normalization (
  arXiv  Detail & Related papers  (2020-04-02T10:14:27Z)

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.