v1v2 (latest)

Characterising Bias in Compressed Models

6 October 2020

ArXiv (abs)PDF HTML HuggingFace (1 upvotes)

Papers citing "Characterising Bias in Compressed Models"

43 / 143 papers shown

Title
Membership Inference Attacks and Defenses in Neural Network PruningUSENIX Security Symposium (USENIX Security), 2022 Xiaoyong Yuan Lan Zhang AAML 158 53 0 07 Feb 2022
Bias in Automated Speaker RecognitionConference on Fairness, Accountability and Transparency (FAccT), 2022 Wiebke Toussaint Aaron Yi Ding CVBM 169 47 0 24 Jan 2022
Can Model Compression Improve NLP Fairness Guangxuan Xu Qingyuan Hu 128 30 0 21 Jan 2022
The Effect of Model Compression on Fairness in Facial Expression Recognition Samuil Stoychev Hatice Gunes CVBM 171 24 0 05 Jan 2022
AI and the Everything in the Whole Wide World Benchmark Inioluwa Deborah Raji Emily M. Bender Amandalynne Paullada Emily L. Denton A. Hanna 228 389 0 26 Nov 2021
How Well Do Sparse Imagenet Models Transfer?Computer Vision and Pattern Recognition (CVPR), 2021 Eugenia Iofinova Alexandra Peste Mark Kurtz Dan Alistarh 357 49 0 26 Nov 2021
DP-REC: Private & Communication-Efficient Federated Learning Aleksei Triastcyn M. Reisser Christos Louizos FedML 153 18 0 09 Nov 2021
LMdiff: A Visual Diff Tool to Compare Language ModelsConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 Hendrik Strobelt Benjamin Hoover Arvind Satyanarayan Sebastian Gehrmann VLM 157 21 0 02 Nov 2021
On the Current and Emerging Challenges of Developing Fair and Ethical AI Solutions in Financial ServicesInternational Conference on AI in Finance (ICAF), 2021 Eren Kurshan Jiahao Chen Victor Storchan Hongda Shen FaML AIFin 193 15 0 02 Nov 2021
NxMTransformer: Semi-Structured Sparsification for Natural Language Understanding via ADMMNeural Information Processing Systems (NeurIPS), 2021 Connor Holmes Minjia Zhang Yuxiong He Bo Wu 107 24 0 28 Oct 2021
Demystifying and Generalizing BinaryConnectNeural Information Processing Systems (NeurIPS), 2021 Abhishek Sharma Yaoliang Yu Eyyub Sari Mahdi Zolnouri V. Nia MQ 166 11 0 25 Oct 2021
Robustness Challenges in Model Distillation and Pruning for Natural Language Understanding Mengnan Du Subhabrata Mukherjee Yu Cheng Milad Shokouhi Helen Zhou Ahmed Hassan Awadallah 206 18 0 16 Oct 2021
The Rich Get Richer: Disparate Impact of Semi-Supervised LearningInternational Conference on Learning Representations (ICLR), 2021 Zhaowei Zhu Tianyi Luo Yang Liu 461 42 0 12 Oct 2021
Measure Twice, Cut Once: Quantifying Bias and Fairness in Deep Neural Networks Cody Blakeney G. Atkinson Nathaniel Huish Yan Yan V. Metsis Ziliang Zong 98 3 0 08 Oct 2021
The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation Orevaoghene Ahia Julia Kreutzer Sara Hooker 294 58 0 06 Oct 2021
General Cross-Architecture Distillation of Pretrained Language Models into Matrix Embeddings Lukas Galke Isabelle Cuber Christophe Meyer Henrik Ferdinand Nolscher Angelina Sonderecker A. Scherp 182 2 0 17 Sep 2021
Avoiding Inference Heuristics in Few-shot Prompt-based FinetuningConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 Prasetya Ajie Utama N. Moosavi Victor Sanh Iryna Gurevych AAML 198 36 0 09 Sep 2021
Hi, my name is Martha: Using names to measure and mitigate bias in generative dialogue models Eric Michael Smith Adina Williams 210 31 0 07 Sep 2021
Beyond Preserved Accuracy: Evaluating Loyalty and Robustness of BERT CompressionConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 Canwen Xu Wangchunshu Zhou Tao Ge Kelvin J. Xu Julian McAuley Furu Wei 212 46 0 07 Sep 2021
Your fairness may vary: Pretrained language model fairness in toxic text classification Ioana Baldini Dennis L. Wei Karthikeyan N. Ramamurthy Mikhail Yurochkin Moninder Singh 359 55 0 03 Aug 2021
A Tale Of Two Long Tails Daniel D'souza Zach Nussbaum Chirag Agarwal Sara Hooker 152 24 0 27 Jul 2021
Randomness In Neural Network Training: Characterizing The Impact of ToolingConference on Machine Learning and Systems (MLSys), 2021 Donglin Zhuang Xingyao Zhang Shuaiwen Leon Song Sara Hooker 198 86 0 22 Jun 2021
Deep Learning Through the Lens of Example DifficultyNeural Information Processing Systems (NeurIPS), 2021 R. Baldock Hartmut Maennel Behnam Neyshabur 259 179 0 17 Jun 2021
Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better Gaurav Menghani VLM MedIm 249 510 0 16 Jun 2021
Masked Training of Neural Networks with Partial Gradients Amirkeivan Mohtashami Martin Jaggi Sebastian U. Stich 303 28 0 16 Jun 2021
Simon Says: Evaluating and Mitigating Bias in Pruned Neural Networks with Knowledge Distillation Cody Blakeney Nathaniel Huish Yan Yan Ziliang Zong 111 19 0 15 Jun 2021
BERT Learns to Teach: Knowledge Distillation with Meta LearningAnnual Meeting of the Association for Computational Linguistics (ACL), 2021 Wangchunshu Zhou Canwen Xu Julian McAuley 255 103 0 08 Jun 2021
Efficient Lottery Ticket Finding: Less Data is MoreInternational Conference on Machine Learning (ICML), 2021 Zhenyu Zhang Xuxi Chen Tianlong Chen Zinan Lin 156 57 0 06 Jun 2021
Can Subnetwork Structure be the Key to Out-of-Distribution Generalization?International Conference on Machine Learning (ICML), 2021 Dinghuai Zhang Kartik Ahuja Yilun Xu Yisen Wang Aaron Courville OOD 237 104 0 05 Jun 2021
Using Pareto Simulated Annealing to Address Algorithmic Bias in Machine Learning William Blanzeisky Padraig Cunningham FaML 147 8 0 31 May 2021
Transitioning from Real to Synthetic data: Quantifying the bias in model Aman Gupta Deepak L. Bhatt Anubha Pandey 134 19 0 10 May 2021
Algorithmic Factors Influencing Bias in Machine Learning William Blanzeisky Padraig Cunningham FaML 104 26 0 28 Apr 2021
In Defense of the Paper Owen Lockwood 63 0 0 16 Apr 2021
An Information-Theoretic Justification for Model PruningInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2021 Berivan Isik Tsachy Weissman Albert No 294 39 0 16 Feb 2021
Scaling Up Exact Neural Network Compression by ReLU StabilityNeural Information Processing Systems (NeurIPS), 2021 Thiago Serra Xin Yu Abhinav Kumar Srikumar Ramalingam 263 26 0 15 Feb 2021
Neural Network Compression for Noisy Storage DevicesACM Transactions on Embedded Computing Systems (TECS), 2021 Berivan Isik Kristy Choi Xin-Yang Zheng Tsachy Weissman Stefano Ermon H. P. Wong Armin Alaghi 174 13 0 15 Feb 2021
Generative Zero-shot Network Quantization Xiangyu He Qinghao Hu Peisong Wang Jian Cheng GAN MQ 187 26 0 21 Jan 2021
Going Beyond Classification Accuracy Metrics in Model Compression Vinu Joseph Shoaib Ahmed Siddiqui Aditya Bhaskara Ganesh Gopalakrishnan Saurav Muralidharan M. Garland Sheraz Ahmed Andreas Dengel 133 18 0 03 Dec 2020
Data-Efficient Pretraining via Contrastive Self-Supervision Nils Rethmeier Isabelle Augenstein 387 22 0 02 Oct 2020
Estimating Example Difficulty Using Variance of GradientsComputer Vision and Pattern Recognition (CVPR), 2020 Chirag Agarwal Daniel D'souza Sara Hooker 534 122 0 26 Aug 2020
Knowledge Distillation in Deep Learning and its ApplicationsPeerJ Computer Science (PeerJ Comput. Sci.), 2020 Abdolmaged Alkhulaifi Fahad Alsahli Irfan Ahmad FedML 136 102 0 17 Jul 2020
Subpopulation Data Poisoning AttacksConference on Computer and Communications Security (CCS), 2020 Matthew Jagielski Giorgio Severi Niklas Pousette Harger Alina Oprea AAML SILM 207 136 0 24 Jun 2020
Who's responsible? Jointly quantifying the contribution of the learning algorithm and training dataAAAI/ACM Conference on AI, Ethics, and Society (AIES), 2019 G. Yona Amirata Ghorbani James Zou TDI 126 15 0 09 Oct 2019