mlsanityData to 7 Oct 2026

Minimizing Energy Consumption of Deep Learning Models by Energy-Aware Training

arXiv 2307.00368 ↗First posted 1 Jul 2023cs.LG cs.AI cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Deep learning models undergo a significant increase in the number of parameters they possess, leading to the execution of a larger number of operations during inference. This expansion significantly contributes to higher energy consumption and prediction latency. In this work, we propose EAT, a gradient-based algorithm that aims to reduce energy consumption during model training. To this end, we leverage a differentiable approximation of the ℓ0 norm, and use it as a sparse penalty over the training loss. Through our experimental analysis conducted on three datasets and two deep neural networks, we demonstrate that our energy-aware training algorithm EAT is able to train networks with a better trade-off between classification performance and energy efficiency.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 20 of its 30 references that are in the map. First posted on arXiv 1 Jul 2023.

Builds on

20 of 30 references.

References · 20

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  4. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,250
  5. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  6. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
  7. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 673
  8. 2020Input-Aware Dynamic Backdoor Attackcited by 304
  9. 2016EIE: Efficient Inference Engine on Compressed Deep Neural Networkcited by 291
  10. 2016Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architecturescited by 220
  11. 2017Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weightscited by 211
  12. 2018Learning to Quantize Deep Networks by Optimizing Quantization Intervals with Task Losscited by 157
8 more
  1. 2017SCNN: An Accelerator for Compressed-sparse Convolutional Neural Networkscited by 132
  2. 2020Sponge Examples: Energy-Latency Attacks on Neural Networkscited by 108
  3. 2022Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoningcited by 93
  4. 2018AutoPruner: An End-to-End Trainable Filter Pruning Method for Efficient Deep Model Inferencecited by 77
  5. 2022Energy-Latency Attacks via Sponge Poisoningcited by 29
  6. 2022Machine Learning Security against Data Poisoning: Are We There Yet?cited by 23
  7. 2021The Hammer and the Nut: Is Bilevel Optimization Really Needed to Poison Linear Classifiers?cited by 9
  8. 2019Online Filter Clustering and Pruning for Efficient Convnetscited by 6

Built on by

Cited by year

Citing papers per year: 2024: 3.

3 papers.

  1. 2024σ-zero: Gradient-based Optimization of ℓ0-norm Adversarial Examplescited by 7
  2. 2024From PEFT to DEFT: Parameter Efficient Finetuning for Reducing Activation Density in Transformerscited by 4
  3. 2024Protein pathways as a catalyst to directed evolution of the topology of artificial neural networkscited by 0