New statistical mechanics analysis shows edge pruning outperforms node pruning in neural networks.
problem Theoretical understanding of neural network pruning effectiveness is lacking.
method Statistical mechanics analysis of a teacher-student framework.
result DPP node pruning method is superior to other methods, but edge pruning is better overall.
This work presents deep asymmetric networks with a set of node-wise variant activation functions. The nodes' sensitivities are affected by activation function selections such that the nodes with smaller indices become increasingly more sensitive. As a result, features learned by the nodes are sorted by the node indices…
We propose a new random pruning method (called "submodular sparsification (SS)") to reduce the cost of submodular maximization. The pruning is applied via a "submodularity graph" over the n ground elements, where each directed edge is associated with a pairwise dependency defined by the submodular function. In each s…
Efficient algorithm removes redundant nodes and obsolete samples in machine learning.
problem Pruning redundant nodes and removing obsolete training samples in machine learning.
method Deduced decremented learning algorithms from incremental learning algorithms, using inverse Cholesterol factor and unitary transformation.
result Proposed decremented learning algorithms efficiently prune redundant nodes and remove obsolete training samples.
Pruning is one of the most effective model reduction techniques. Deep networks require massive computation and such models need to be compressed to bring them on edge devices. Most existing pruning techniques are focused on vision-based models like convolutional networks, while text-based models are still evolving. The…
In this paper we study predictive pattern mining problems where the goal is to construct a predictive model based on a subset of predictive patterns in the database. Our main contribution is to introduce a novel method called safe pattern pruning (SPP) for a class of predictive pattern mining problems. The SPP method a…
Neural network for subgraph similarity computation with pruning.
problem Computing subgraph similarity between a target and query graph.
method Convert pruning to node relabeling, relax to differentiable problem, design neural network for SED computation.
result Establishes new state-of-the-art results across multiple benchmark datasets.
ForestPrune optimizes tree ensemble pruning for compactness and speed.
problem Large tree ensembles in predictive models consume excessive memory and reduce interpretability.
method Developed a specialized optimization algorithm to efficiently prune tree ensembles by depth layers.
result ForestPrune produces compact, high-performing models that outperform existing post-processing methods.
Graph pruning improves neural network performance by addressing squashing and smoothing issues.
problem Over-squashing and over-smoothing in Graph Neural Networks.
method Proposes edge deletions to simultaneously address over-squashing and over-smoothing, optimizing spectral gap.
result Edge deletions improve generalization and distinguishability of nodes of different classes.
Bayesian neural networks are compressed using feature and weight pruning based on posterior inclusion probabilities.
problem Efficiently compressing Bayesian neural networks to reduce computation cost and improve generalizability.
method Bayesian model selection principles are applied to obtain posterior inclusion probabilities for pruning and feature selection.
result Pruned models show better generalizability on simulated and real-world data.
Pruning FCNs reveals sub-networks that match CNNs' performance.
problem Understanding the inductive bias of pruning in neural networks.
method Iterative magnitude pruning of a simple FCN followed by analysis of the resulting architecture.
result Pruned FCNs exhibit key features of CNNs, suggesting new architectural biases.
RicciNets prunes neural networks by removing edges of low importance based on Ricci curvature, reducing FLOPs by 35%.
problem Pruning neural networks to reduce computational load and improve efficiency.
method RicciNets uses Ricci curvature to prune edges of low importance in a randomly wired neural network, reducing FLOPs.
result Reduction of almost 35% in FLOPs with no performance degradation.
Improves parallel deep model performance by restructuring and pruning.
problem Latency in parallel deep model execution due to interdependency among sub-models.
method Layer-wise model restructuring and pruning, using ℓ0 optimization and Munkres assignment algorithm. result Significantly improves efficiency of distributed inference in terms of communication and computational complexity.
Proposes a Bayesian approach for automatic node selection in sparse neural networks.
problem Reduces structural complexity and computational speedup in large-scale predictive models.
method Uses spike-and-slab Gaussian priors and variational Bayes approach for node selection.
result Establishes variational posterior consistency and optimal contraction rates for sparse networks.
PAC-MCTS addresses biased search in LLM-guided planning by dynamically pruning.
problem Systematic biases in LLMs lead to inefficient and unsafe search in deep planning tasks.
method Formulates node expansion as BAI under bounded bias, derives sample complexity bounds, and proposes PAC-MCTS for dynamic confidence bounds.
result PAC-MCTS improves robustness and efficiency by up to 78% fewer API evaluations and 3x higher sample efficiency.
It is inevitable to train large deep learning models on a large-scale cluster equipped with accelerators system. Deep gradient compression would highly increase the bandwidth utilization and speed up the training process but hard to implement on ring structure. In this paper, we find that redundant gradient and gradien…
For decomposable score-based structure learning of Bayesian networks, existing approaches first compute a collection of candidate parent sets for each variable and then optimize over this collection by choosing one parent set for each variable without creating directed cycles while maximizing the total score. We target…
New method speeds up solving L0-regularized least-squares problems.
problem Solving L0-regularized least-squares problems efficiently.
method Safe peeling for Branch-and-Bound algorithm.
result Significant gains in solving time and node exploration.
Compression and computational efficiency in deep learning have become a problem of great significance. In this work, we argue that the most principled and effective way to attack this problem is by adopting a Bayesian point of view, where through sparsity inducing priors we prune large parts of the network. We introduc…
A new algorithm reduces communication in decentralized optimization.
problem Reducing communication in decentralized optimization problems.
method Adaptive randomized communication-efficient algorithmic framework that periodically tracks disagreement error and selects influential edges for communication.
result Strong theoretical convergence guarantees and performance quantification under standard assumptions.
MBExplainer provides explanations for models combining graph embeddings and tabular features.
problem Explaining models using a mix of graph embeddings and tabular features.
method Model-agnostic approach using Shapley values and Monte Carlo Tree Search.
result MBExplainer efficiently finds human-readable explanations for model predictions.
Study of local optima in neural networks for feature interactions.
problem NNs struggle with local optima in feature interactions for small datasets.
method Proposed a node pruning and feature selection algorithm to improve NN performance.
result NNs have many non-equivalent local optima in XOR-like data with irrelevant variables.
The paper studies statistical properties of CART regression trees.
problem Understanding the statistical properties of CART regression trees.
method The paper constructs a prior distribution on split points and solves a nonlinear optimization problem to bound the Pearson correlation between the optimal decision stump and response data.
result CART with cost-complexity pruning achieves an optimal complexity/goodness-of-fit tradeoff when the depth scales with the logarithm of the sample size.
Paper proposes a multi-phase pruning pipeline for deep ensemble learning on IIoT devices.
problem Computational limitations of IoT devices for deep learning models.
method Generates diverse pruned models, applies integer quantization, and uses clustering-based pruning.
result Significant reduction in model size (up to 90%) and improved performance (up to 7%) on IIoT devices.
Compression techniques for deep neural network models are becoming very important for the efficient execution of high-performance deep learning systems on edge-computing devices. The concept of model compression is also important for analyzing the generalization error of deep learning, known as the compression-based er…
FastGAT reduces GNN computation time by 10x using graph sparsification.
problem High computational burden in attention-based GNNs.
method Spectral sparsification to generate optimal graph pruning.
result Per-epoch time is almost linear in graph nodes, reducing computational time by up to 10x.
Taking into account high-order interactions among covariates is valuable in many practical regression problems. This is, however, computationally challenging task because the number of high-order interaction features to be considered would be extremely large unless the number of covariates is sufficiently small. In thi…
EAST compresses deep ConvNets for tiny memory nodes.
problem Memory constraints in tiny devices for deep ConvNets.
method Encoding-Aware Sparse Training (EAST) with adaptive group pruning and LZ4 weight encoding.
result EAST achieves deep memory compression with lower sparsity and higher accuracy.
NDP improves GNN efficiency by coarsening graphs without losing structure.
problem Efficiently summarize graph data for deep learning models.
method Node Decimation Pooling (NDP) reduces graph density while preserving topology.
result NDP achieves comparable performance to state-of-the-art pooling methods but with improved efficiency.
SEG-BERT improves graph instance learning by adapting GRAPH-BERT.
problem Graph instance representation learning challenges due to diverse sizes and node order.
method Adapted GRAPH-BERT with a segmented architecture to handle graph node orderlessness and diverse sizes.
result SEG-BERT outperforms comparison methods on six out of seven benchmark datasets.
Lookahead pruning extends single-layer optimization to multi-layer, outperforming magnitude-based pruning.
problem Pruning neural networks to reduce computational cost and memory usage.
method Developed a multi-layer optimization approach extending the single-layer optimization of magnitude-based pruning.
result Consistently outperforms magnitude-based pruning on various networks, especially in high sparsity.
New algorithm speeds up causal discovery for network data.
problem Scalability issues in score-matching for temporal network data.
method Developed a new parent-finding subroutine for DAGs, improving score matching efficiency.
result Efficiency-lifted score matching for both i.i.d. and temporal data on networks.
PILOT is a fast algorithm for linear model trees that outperforms existing methods.
problem Fitting linear model trees to large datasets efficiently and accurately.
method Greedy training with L2 boosting and model selection rule. result PILOT outperforms standard decision trees and other linear model trees on various datasets.
Recent pruning methods at initialization fall short of random pruning's accuracy.
problem Improving neural network accuracy through pruning at initialization.
method Various pruning methods (SNIP, GraSP, SynFlow, magnitude pruning) are evaluated; per-layer pruning decisions are proposed.
result Randomly shuffling or sampling initial weights preserves or improves accuracy, suggesting challenges with pruning heuristics.
ICE-Pruning accelerates deep neural network pruning by 9.61x.
problem Efficiently pruning deep neural networks while maintaining accuracy.
method Iterative pruning with automatic fine-tuning steps, freezing strategy, and custom learning rate scheduler.
result Significantly reduces pruning time by up to 9.61x.
DSA efficiently allocates sparsity across layers for budgeted pruning.
problem Efficiently distributing resources (sparsity) across layers in pruning under resource constraints.
method DSA uses differentiable pruning to find continuous layer-wise pruning ratios via gradient-based optimization.
result DSA achieves superior performance and significantly reduces the time cost of pruning.
Study examines effects of pruning techniques on deep learning models.
problem Understanding the impact of pruning methods on deep learning model structure and dynamics.
method Investigated differences in connectivity and learning dynamics of pruned models using various iterative pruning techniques.
result Emergence of structure in pruned models through magnitude-based unstructured pruning and weight rewinding.
ELMs benefit from using equal number of hidden nodes to training samples.
problem Overfitting and underfitting in ELMs with hidden nodes.
method ELMs with hidden nodes equal to training samples achieve perfect training.
result ELMs with larger hidden nodes outperform traditional ELMs.
Pruning neural network parameters is often viewed as a means to compress models, but pruning has also been motivated by the desire to prevent overfitting. This motivation is particularly relevant given the perhaps surprising observation that a wide variety of pruning approaches increase test accuracy despite sometimes …
Dynamic pruning during training reduces deep network complexity without significant accuracy loss.
problem High memory and computational requirements of deep networks during training and inference.
method Dynamic pruning of convolutional filters during training, using L1 normalization for optimization.
result L1 normalization-based pruning yields up to 50% reduction in filters with minimal accuracy loss.
The study reveals flaws in pruning criteria and proposes a new assumption for better filter selection.
problem Flaws in existing pruning criteria for CNNs.
method Empirical experiments and Convolutional Weight Distribution Assumption.
result The Convolutional Weight Distribution Assumption improves filter selection in pruning.
SGAS improves neural architecture search by choosing and pruning operations greedily.
problem NAS often fails to generalize in final evaluation.
method Divides search into sub-problems and chooses/prunes candidate operations greedily.
result SGAS finds state-of-the-art architectures with minimal computational cost.
Deep neural networks have dramatically achieved great success on a variety of challenging tasks. However, most successful DNNs have an extremely complex structure, leading to extensive research on model compression.As a significant area of progress in model compression, traditional gradual pruning approaches involve an…
Gibbs pruning optimizes neural networks by combining physics and regularization.
problem Large neural networks are impractical for many applications.
method Combines statistical physics and stochastic regularization to train and prune networks simultaneously.
result Gibbs pruning achieves state-of-the-art performance on ResNet-56.
This paper introduces blind adversarial pruning to balance accuracy, efficiency, and robustness in neural networks.
problem Balancing accuracy, efficiency, and robustness in neural networks with limited resources.
method Adversarial pruning with a cutoff-scale strategy to dynamically adjust the strength of adversarial examples.
result Blind adversarial pruning improves the overall AER of pruned models compared to adversarial pruning.
Speeds up training and inference by pruning entire channels before training.
problem Training and inference speed in deep neural networks.
method Structured pruning applied before training, focusing on removing entire channels and hidden units.
result 2x speedup in training and 3x speedup in inference.
This paper analyzes privacy risks in neural network pruning and proposes a defense mechanism.
problem Privacy risks in neural network pruning due to membership inference attacks.
method Investigates the impact of pruning on prediction divergence and proposes a self-attention membership inference attack.
result Proposed defense mechanism mitigates privacy risks while maintaining sparsity and accuracy.
Neural network pruning lacks standardized benchmarks and metrics.
problem Lack of standardized benchmarks and metrics in neural network pruning.
method Meta-analysis of 81 papers, controlled conditions, ShrinkBench framework.
result Neural network pruning community lacks standardized benchmarks and metrics.