paper-with-me

홈 › Papers

The Other Side of Compression: Measuring Bias in Pruned Transformers

2023-04-01 · Advances in Intelligent Data Analysis XXI 2023 4 · Irina Proskurina, Guillaume Metzler, Julien Velcin

Social media platforms have become popular worldwide. Online discussion forums attract users because of their easy access, speech freedom, and ease of communication. Yet there are also possible negative aspects of such communication, including hostile and hate language. While fast and effective solutions for detecting inappropriate language online are constantly being developed, there is little research focusing on the bias of compressed language models that are commonly used nowadays. In this work, we evaluate bias in compressed models trained on Gab and Twitter hatespeech data and estimate to which extent these pruned models capture the relevant context when classifying the input text as hateful, offensive or neutral. Results of our experiments show that transformer-based encoders with 70% or fewer preserved weights are prone to gender, racial, and religious identity-based bias, even if the performance loss is insignificant. We suggest a supervised attention mechanism to counter bias amplification using ground truth per-token hate speech annotation. The proposed method allows pruning BERT, RoBERTa and their distilled versions up to 50% while preserving 90% of their initial performance according to bias and plausibility scores.

📄 PDF Abstract BibTeX

Code (1)

upunaprosk/fair-pruning pytorch

Tasks

Hate Speech DetectionNetwork Pruning

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Multi-Head Attention 설명 없음
Attention 설명 없음
Weight Decay 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
WordPiece 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures

2023-04-25 · CVPR 2023 1 · Eugenia Iofinova, Alexandra Peste, Dan Alistarh

Pruning - that is, setting a significant subset of the parameters of a neural network to zero - is one of the most popular methods of model compression. Yet, several recent works have raised the issue that pruning may in…

Model CompressionNetwork Pruning

Linearity-based neural network compression

2025-06-26 · Silas Dobler, Florian Lemmerich

In neural network compression, most current methods reduce unnecessary parameters by measuring importance and redundancy. To augment already highly optimized existing solutions, we propose linearity-based compression as …

Efficient Neural NetworkNeural Network Compression

Data-Free Backbone Fine-Tuning for Pruned Neural Networks

2023-06-22 · Adrian Holzbock, Achyut Hegde, Klaus Dietmayer, Vasileios Belagiannis

Model compression techniques reduce the computational load and memory consumption of deep neural networks. After the compression operation, e.g. parameter pruning, the model is normally fine-tuned on the original trainin…

2D Human Pose Estimationimage-classificationImage ClassificationModel Compression+3

Win the Lottery Ticket via Fourier Analysis: Frequencies Guided Network Pruning

2022-01-30 · Yuzhang Shang, Bin Duan, Ziliang Zong, Liqiang Nie 외

With the remarkable success of deep learning recently, efficient network compression algorithms are urgently demanded for releasing the potential computational power of edge devices, such as smartphones or tablets. Howev…

Knowledge DistillationNetwork Pruning

Pruning Convolutional Neural Networks for Image Instance Retrieval

2017-07-18 · Gaurav Manek, Jie Lin, Vijay Chandrasekhar, Ling-Yu Duan 외

In this work, we focus on the problem of image instance retrieval with deep descriptors extracted from pruned Convolutional Neural Networks (CNN). The objective is to heavily prune convolutional edges while maintaining r…

Image Instance RetrievalRetrievalTriplet