paper-with-me

홈 › Papers

Selective Brain Damage: Measuring the Disparate Impact of Model Pruning

2019-09-25 · Sara Hooker, Yann Dauphin, Aaron Courville, Andrea Frome

Neural network pruning techniques have demonstrated it is possible to remove the majority of weights in a network with surprisingly little degradation to top-1 test set accuracy. However, this measure of performance conceals significant differences in how different classes and images are impacted by pruning. We find that certain individual data points, which we term pruning identified exemplars (PIEs), and classes are systematically more impacted by the introduction of sparsity. Removing PIE images from the test-set greatly improves top-1 accuracy for both sparse and non-sparse models. These hard-to-generalize-to images tend to be of lower image quality, mislabelled, entail abstract representations, require fine-grained classification or depict atypical class examples.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Network Pruning

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Local White Matter Architecture Defines Functional Brain Dynamics

2018-04-22 · Yo Joong Choe, Sivaraman Balakrishnan, Aarti Singh, Jean M. Vettel 외

Large bundles of myelinated axons, called white matter, anatomically connect disparate brain regions together and compose the structural core of the human connectome. We recently proposed a method of measuring the local …

Functional ConnectivityVariable Selection

From Biased Selective Labels to Pseudo-Labels: An Expectation-Maximization Framework for Learning from Biased Decisions

2024-06-27 · Trenton Chang, Jenna Wiens

Selective labels occur when label observations are subject to a decision-making process; e.g., diagnoses that depend on the administration of laboratory tests. We study a clinically-inspired selective label problem calle…

Decision MakingDiagnostic

Relationship between brain injury criteria and brain strain across different types of head impacts can be different

2020-12-18 · Xianghao Zhan, Yiheng Li, Yuzhe Liu, August G. Domel 외

Multiple brain injury criteria (BIC) are developed to quickly quantify brain injury risks after head impacts. These BIC originated from different types of head impacts (e.g., sports and car crashes) are widely used in ri…

regression

FAIRLABEL: Correcting Bias in Labels

2023-11-01 · Srinivasan H Sengamedu, Hien Pham

There are several algorithms for measuring fairness of ML models. A fundamental assumption in these approaches is that the ground truth is fair or unbiased. In real-world datasets, however, the ground truth often contain…

Fairness

OBCache: Optimal Brain KV Cache Pruning for Efficient Long-Context LLM Inference

2025-10-09 · Yuzhe Gu, Xiyu Liang, Jiaojiao Zhao, Enmao Diao arxiv

Large language models (LLMs) with extended context windows enable powerful applications but impose significant memory overhead, as caching all key-value (KV) states scales linearly with sequence length and batch size. Ex…