Position: Tensor Networks are a Valuable Asset for Green AI
Not on the map. Why?
Abstract (arXiv)
For the first time, this position paper introduces a fundamental link between tensor networks (TNs) and Green AI, highlighting their synergistic potential to enhance both the inclusivity and sustainability of AI research. We argue that TNs are valuable for Green AI due to their strong mathematical backbone and inherent logarithmic compression potential. We undertake a comprehensive review of the ongoing discussions on Green AI, emphasizing the importance of sustainability and inclusivity in AI research to demonstrate the significance of establishing the link between Green AI and TNs. To support our position, we first provide a comprehensive overview of efficiency metrics proposed in Green AI literature and then evaluate examples of TNs in the fields of kernel machines and deep learning using the proposed efficiency metrics. This position paper aims to incentivize meaningful, constructive discussions by bridging fundamental principles of Green AI and TNs. We advocate for researchers to seriously evaluate the integration of TNs into their research projects, and in alignment with the link established in this paper, we support prior calls encouraging researchers to treat Green AI principles as a research priority.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 53 of its 104 references that are in the map. First posted on arXiv 25 May 2022.
Builds on
53 of 104 references.
References · 53
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,262
- 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,254
- 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 815
- 2017Deep Neural Networks as Gaussian Processescited by 622
- 2022Scientific Machine Learning through Physics-Informed Neural Networks: Where we are and What's nextcited by 608
- 2019Quantifying the Carbon Emissions of Machine Learningcited by 521
- 2013Gaussian Processes for Big Datacited by 383
- 2014Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluationcited by 306
- 2014Speeding up Convolutional Neural Networks with Low Rank Expansionscited by 284
38 more
- 2015Tensorizing Neural Networkscited by 250
- 2020Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learningcited by 249
- 2021Sustainable AI: Environmental Implications, Challenges and Opportunitiescited by 242
- 2016Tensor Decomposition for Signal Processing and Machine Learningcited by 224
- 2022Predictability and Surprise in Large Generative Modelscited by 210
- 2014Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decompositioncited by 203
- 2020The Computational Limits of Deep Learningcited by 193
- 2020On Hyperparameter Optimization of Machine Learning Algorithms: Theory and Practicecited by 182
- 2018Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processescited by 167
- 2015Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applicationscited by 162
- 2021Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challengescited by 145
- 2018Deep Convolutional Networks as shallow Gaussian Processescited by 138
- 2019A Tensorized Transformer for Language Modelingcited by 86
- 2020Chasing Carbon: The Elusive Environmental Footprint of Computingcited by 72
- 2017Tensor-Train Recurrent Neural Networks for Video Classificationcited by 59
- 2016Ultimate tensorization: compressing convolutional and FC layers alikecited by 56
- 2017Tensor Networks for Dimensionality Reduction and Large-Scale Optimizations. Part 2 Applications and Future Perspectivescited by 54
- 2020Measuring the Algorithmic Efficiency of Neural Networkscited by 52
- 2021Tensor Methods in Computer Vision and Deep Learningcited by 52
- 2021Towards Efficient Tensor Decomposition-Based DNN Model Compression with Optimization Frameworkcited by 52
- 2016Higher-Order Factorization Machinescited by 45
- 2019Energy Usage Reports: Environmental awareness as part of algorithmic accountabilitycited by 44
- 2019Factorized Higher-Order CNNs with an Application to Spatio-Temporal Emotion Estimationcited by 40
- 2016Supervised Learning with Quantum-Inspired Tensor Networkscited by 36
- 2017Learning Compact Recurrent Neural Networks with Block-Term Tensor Decompositioncited by 33
- 2017CP-decomposition with Tensor Power Method for Convolutional Neural Networks Compressioncited by 30
- 2020Tensor Low-Rank Reconstruction for Semantic Segmentationcited by 29
- 2017Compressing Recurrent Neural Network with Tensor Traincited by 28
- 2017Scalable Gaussian Processes with Billions of Inducing Inputs via Tensor Train Decompositioncited by 28
- 2021Solving high-dimensional parabolic PDEs using the tensor train formatcited by 17
- 2016Parallelized Tensor Train Learning of Polynomial Classifierscited by 16
- 2020Hybrid Tensor Decomposition in Neural Network Compressioncited by 15
- 2021Large-Scale Learning with Fourier Features and Tensor Decompositionscited by 14
- 2016Tensor Network alternating linear scheme for MIMO Volterra system identificationcited by 13
- 2018Boosted Sparse and Low-Rank Tensor Regressioncited by 9
- 2019Compression and Interpretability of Deep Neural Networks via Tucker Tensor Layer: From First Principles to Tensor Valued Back-Propagationcited by 9
- 2020Nonlinear system identification with regularized Tensor Network B-splinescited by 7
- 2021Low-rank Tensor Decomposition for Compression of Convolutional Neural Networks Using Funnel Regularizationcited by 6
50 most cited of 53 All 53 (JSON)
Built on by
Citing papers per year: 2025: 3.
3 papers.