v1v2 (latest)

Characterising Bias in Compressed Models

6 October 2020

ArXiv (abs)PDF HTML HuggingFace (1 upvotes)

Papers citing "Characterising Bias in Compressed Models"

50 / 143 papers shown

Title
Model Compression in Practice: Lessons Learned from Practitioners Creating On-device Machine Learning ExperiencesInternational Conference on Human Factors in Computing Systems (CHI), 2023 Fred Hohman Mary Beth Kery Donghao Ren Dominik Moritz 329 25 0 06 Oct 2023
Uncovering the Hidden Cost of Model Compression Diganta Misra Muawiz Chaudhary Agam Goyal Bharat Runwal Pin-Yu Chen VLM 273 3 0 29 Aug 2023
Compressed Models Decompress Race Biases: What Quantized Models Forget for Fair Face RecognitionBiometrics and Electronic Signatures (BES), 2023 Pedro C. Neto Eduarda Caldeira Jaime S. Cardoso Ana F. Sequeira MQ 155 15 0 23 Aug 2023
Accurate Neural Network Pruning Requires Rethinking Sparse Optimization Denis Kuznedelev Eldar Kurtic Eugenia Iofinova Elias Frantar Alexandra Peste Dan Alistarh VLM 320 14 0 03 Aug 2023
Self-Distilled Quantization: Achieving High Compression Rates in Transformer-Based Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 James OÑeill Sourav Dutta VLM MQ 160 1 0 12 Jul 2023
On The Impact of Machine Learning Randomness on Group FairnessConference on Fairness, Accountability and Transparency (FAccT), 2023 Prakhar Ganesh Hong Chang Martin Strobel Reza Shokri FaML 228 39 0 09 Jul 2023
Pruning vs Quantization: Which is Better?Neural Information Processing Systems (NeurIPS), 2023 Andrey Kuzmin Markus Nagel M. V. Baalen Arash Behboodi Tijmen Blankevoort MQ 300 100 0 06 Jul 2023
Sparse Model Soups: A Recipe for Improved Pruning via Model AveragingInternational Conference on Learning Representations (ICLR), 2023 Max Zimmer Christoph Spiegel Sebastian Pokutta MoMe 467 18 0 29 Jun 2023
Evaluating the Social Impact of Generative AI Systems in Systems and Society Irene Solaiman Zeerak Talat William Agnew Lama Ahmad Dylan K. Baker ... Marie-Therese Png Shubham Singh A. Strait Lukas Struppek Arjun Subramonian ELM EGVM 443 145 0 09 Jun 2023
Augmenting Hessians with Inter-Layer Dependencies for Mixed-Precision Post-Training Quantization Clemens J. S. Schaefer Navid Lambert-Shirzad Xiaofan Zhang Chia-Wei Chou T. Jablin Jian Li Elfie Guo Caitlin Stanton S. Joshi Yu Emma Wang MQ 215 4 0 08 Jun 2023
Query Encoder Distillation via Embedding Alignment is a Strong Baseline Method to Boost Dense Retriever Online Efficiency Yuxuan Wang Hong Lyu 138 3 0 05 Jun 2023
Lottery Tickets in Evolutionary Optimization: On Sparse Backpropagation-Free Trainability R. T. Lange Henning Sprekeler 173 2 0 31 May 2023
Just CHOP: Embarrassingly Simple LLM Compression A. Jha Tom Sherborne Evan Pete Walsh Dirk Groeneveld Emma Strubell Iz Beltagy 217 4 0 24 May 2023
Cross-lingual Transfer Can Worsen Bias in Sentiment AnalysisConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 Seraphina Goldfarb-Tarrant Bjorn Ross Adam Lopez 218 9 0 22 May 2023
A Comprehensive Study on Dataset Distillation: Performance, Privacy, Robustness and Fairness Zongxiong Chen Fauzan Farooqui Derui Zhu Herbert Woisetschlaeger Qing Li Sonja Schimmler Ruben Mayer Chunming Rong DD 211 9 0 05 May 2023
Distill or Annotate? Cost-Efficient Fine-Tuning of Compact ModelsAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 Junmo Kang Wei Xu Alan Ritter 284 16 0 02 May 2023
Cross-Institutional Transfer Learning for Educational Models: Implications for Model Performance, Fairness, and EquityConference on Fairness, Accountability and Transparency (FAccT), 2023 Joshua Gardner Renzhe Yu Quan Nguyen Christopher A. Brooks René F. Kizilcec FedML 173 20 0 01 May 2023
Bias in Pruned Vision Models: In-Depth Analysis and CountermeasuresComputer Vision and Pattern Recognition (CVPR), 2023 Eugenia Iofinova Alexandra Peste Dan Alistarh 237 11 0 25 Apr 2023
Angler: Helping Machine Translation Practitioners Prioritize Model ImprovementsInternational Conference on Human Factors in Computing Systems (CHI), 2023 Samantha Robertson Zijie J. Wang Dominik Moritz Mary Beth Kery Fred Hohman 225 20 0 12 Apr 2023
Do We Train on Test Data? The Impact of Near-Duplicates on License Plate RecognitionIEEE International Joint Conference on Neural Network (IJCNN), 2023 Rayson Laroca Valter Estevam A. Britto Rodrigo Minetto David Menotti 149 14 0 10 Apr 2023
Fairness in Language Models Beyond English: Gaps and ChallengesFindings (Findings), 2023 Krithika Ramesh Sunayana Sitaram Monojit Choudhury 323 27 0 24 Feb 2023
Debiased Distillation by Transplanting the Last Layer Jiwoon Lee Jaeho Lee 135 5 0 22 Feb 2023
Progressive Ensemble Distillation: Building Ensembles for Efficient InferenceNeural Information Processing Systems (NeurIPS), 2023 D. Dennis Abhishek Shetty A. Sevekari K. Koishida Virginia Smith FedML 226 0 0 20 Feb 2023
Counting Carbon: A Survey of Factors Influencing the Emissions of Machine Learning A. Luccioni Alex Hernandez-Garcia 223 70 0 16 Feb 2023
Getting Away with More Network Pruning: From Sparsity to Geometry and Linear RegionsIntegration of AI and OR Techniques in Constraint Programming (CPAIOR), 2023 Junyang Cai Khai-Nguyen Nguyen Nishant Shrestha Aidan Good Ruisen Tu Xin Yu Shandian Zhe Thiago Serra MLT 268 11 0 19 Jan 2023
Undesirable Biases in NLP: Addressing Challenges of Measurement Oskar van der Wal Dominik Bachmann Alina Leidinger L. Maanen Willem H. Zuidema K. Schulz 416 8 0 24 Nov 2022
Fairness Increases Adversarial Vulnerability Cuong Tran Keyu Zhu Ferdinando Fioretto Pascal Van Hentenryck 189 7 0 21 Nov 2022
A Fair Loss Function for Network Pruning Robbie Meyer Alexander Wong CVBM 212 6 0 18 Nov 2022
Bridging Fairness and Environmental Sustainability in Natural Language ProcessingConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 Marius Hessenthaler Emma Strubell Dirk Hovy Anne Lauscher 214 8 0 08 Nov 2022
Intriguing Properties of Compression on Multilingual ModelsConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 Kelechi Ogueji Orevaoghene Ahia Gbemileke Onilude Sebastian Gehrmann Sara Hooker Julia Kreutzer 301 15 0 04 Nov 2022
Pruning's Effect on Generalization Through the Lens of Training and RegularizationNeural Information Processing Systems (NeurIPS), 2022 Tian Jin Michael Carbin Daniel M. Roy Jonathan Frankle Gintare Karolina Dziugaite 212 33 0 25 Oct 2022
Sparse Random Networks for Communication-Efficient Federated LearningInternational Conference on Learning Representations (ICLR), 2022 Berivan Isik Francesco Pase Deniz Gunduz Tsachy Weissman M. Zorzi FedML 211 63 0 30 Sep 2022
Metadata Archaeology: Unearthing Data Subsets by Leveraging Training DynamicsInternational Conference on Learning Representations (ICLR), 2022 Shoaib Ahmed Siddiqui Nitarshan Rajkumar Tegan Maharaj David M. Krueger Sara Hooker 254 33 0 20 Sep 2022
Efficient Methods for Natural Language Processing: A SurveyTransactions of the Association for Computational Linguistics (TACL), 2022 Marcos Vinícius Treviso Ji-Ung Lee Tianchu Ji Betty van Aken Qingqing Cao ... Emma Strubell Niranjan Balasubramanian Leon Derczynski Iryna Gurevych Roy Schwartz 365 140 0 31 Aug 2022
Towards Explaining Demographic Bias through the Eyes of Face Recognition Models Biying Fu Naser Damer 125 12 0 29 Aug 2022
Combining Compressions for Multiplicative Size Scaling on Natural Language TasksInternational Conference on Computational Linguistics (COLING), 2022 Rajiv Movva Jinhao Lei Shayne Longpre Ajay K. Gupta Chris DuBois VLM MQ 151 6 0 20 Aug 2022
FairGRAPE: Fairness-aware GRAdient Pruning mEthod for Face Attribute ClassificationEuropean Conference on Computer Vision (ECCV), 2022 Xiao-Ze Lin Seungbae Kim Jungseock Joo CVBM 222 46 0 22 Jul 2022
Recall Distortion in Neural Network Pruning and the Undecayed Pruning AlgorithmNeural Information Processing Systems (NeurIPS), 2022 Aidan Good Jia-Huei Lin Hannah Sieg Mikey Ferguson Xin Yu Shandian Zhe J. Wieczorek Thiago Serra 286 12 0 07 Jun 2022
Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of ExpertsNeural Information Processing Systems (NeurIPS), 2022 Basil Mustafa C. Riquelme J. Puigcerver Rodolphe Jenatton N. Houlsby VLM MoE 346 272 0 06 Jun 2022
Towards Fair Federated Recommendation Learning: Characterizing the Inter-Dependence of System and Data HeterogeneityACM Conference on Recommender Systems (RecSys), 2022 Kiwan Maeng Haiyu Lu Luca Melis John Nguyen Michael G. Rabbat Carole-Jean Wu FedML 206 37 0 30 May 2022
Pruning has a disparate impact on model accuracyNeural Information Processing Systems (NeurIPS), 2022 Cuong Tran Ferdinando Fioretto Jung-Eun Kim Rakshit Naidu 225 46 0 26 May 2022
Matryoshka Representation LearningNeural Information Processing Systems (NeurIPS), 2022 Aditya Kusupati Gantavya Bhatt Aniket Rege Matthew Wallingford Aditya Sinha ... William Howard-Snyder Kaifeng Chen Sham Kakade Prateek Jain Ali Farhadi 440 165 0 26 May 2022
Train Flat, Then Compress: Sharpness-Aware Minimization Learns More Compressible ModelsConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 Clara Na Sanket Vaibhav Mehta Emma Strubell 259 24 0 25 May 2022
What Do Compressed Multilingual Machine Translation Models Forget?Conference on Empirical Methods in Natural Language Processing (EMNLP), 2022 Alireza Mohammadshahi Vassilina Nikoulina Alexandre Berard Caroline Brun James Henderson Laurent Besacier AI4CE 390 12 0 22 May 2022
Fast Conditional Network Compression Using Bayesian HyperNetworks Phuoc Nguyen T. Tran Ky Le Sunil R. Gupta Santu Rana Dang Nguyen Trong Nguyen S. Ryan Svetha Venkatesh BDL 119 7 0 13 May 2022
The Road to Explainability is Paved with Bias: Measuring the Fairness of ExplanationsConference on Fairness, Accountability and Transparency (FAccT), 2022 Aparna Balagopalan Haoran Zhang Kimia Hamidieh Thomas Hartvigsen Frank Rudzicz Marzyeh Ghassemi 256 90 0 06 May 2022
Holistic Approach to Measure Sample-level Adversarial Vulnerability and its Utility in Building Trustworthy Systems Gaurav Kumar Nayak Ruchit Rawal Rohit Lal Himanshu Patil Anirban Chakraborty AAML 137 2 0 05 May 2022
The Effects of Regularization and Data Augmentation are Class DependentNeural Information Processing Systems (NeurIPS), 2022 Randall Balestriero Léon Bottou Yann LeCun 262 111 0 07 Apr 2022
OccamNets: Mitigating Dataset Bias by Favoring Simpler HypothesesEuropean Conference on Computer Vision (ECCV), 2022 Robik Shrestha Kushal Kafle Christopher Kanan CML 284 14 0 05 Apr 2022
The Combinatorial Brain Surgeon: Pruning Weights That Cancel One Another in Neural NetworksInternational Conference on Machine Learning (ICML), 2022 Xin Yu Thiago Serra Srikumar Ramalingam Shandian Zhe 385 58 0 09 Mar 2022

All Papers

Characterising Bias in Compressed Models

Papers citing "Characterising Bias in Compressed Models"