paper-with-me

홈 › Papers

Effectiveness of MPC-friendly Softmax Replacement

2020-11-23 · Marcel Keller, Ke Sun

Softmax is widely used in deep learning to map some representation to a probability distribution. As it is based on exp/log functions that are relatively expensive in multi-party computation, Mohassel and Zhang (2017) proposed a simpler replacement based on ReLU to be used in secure computation. However, we could not reproduce the accuracy they reported for training on MNIST with three fully connected layers. Later works (e.g., Wagh et al., 2019 and 2021) used the softmax replacement not for computing the output probability distribution but for approximating the gradient in back-propagation. In this work, we analyze the two uses of the replacement and compare them to softmax, both in terms of accuracy and cost in multi-party computation. We found that the replacement only provides a significant speed-up for a one-layer network while it always reduces accuracy, sometimes significantly. Thus we conclude that its usefulness is limited and one should use the original softmax function instead.

📄 PDF Abstract BibTeX arXiv:2011.11202

Code (3)

mkskeller/mnist-mpc 공식 구현 tf
csiro-mlai/deep-mpc tf
csiro-mlai/mnist-mpc tf

Methods 이 논문이 사용한 방법론

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 $x$…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

PADRe: A Unifying Polynomial Attention Drop-in Replacement for Efficient Vision Transformer

2024-07-16 · Pierre-David Letourneau, Manish Kumar Singh, Hsin-Pai Cheng, Shizhong Han 외

We present Polynomial Attention Drop-in Replacement (PADRe), a novel and unifying framework designed to replace the conventional self-attention mechanism in transformer models. Notably, several recent alternative attenti…

2D Object DetectionComputational EfficiencyGPUimage-classification+4

Layer-Parallel Inference Reduces Encrypted Nonlinear Depth in Transformers

2026-07-06 · Ligong Han, Kai Xu, Hao Wang, Ruijiang Gao 외 arxiv

Fully homomorphic encryption (FHE) enables computation on encrypted data, but practical encrypted Transformer inference is bottlenecked by the sequential composition of many nonlinear blocks. We study whether Structured …

IntAttention: A Fully Integer Attention Pipeline for Efficient Edge Inference

2025-11-26 · Wanli Zhong, Haibo Feng, Zirui Zhou, Hanyang Peng 외 arxiv

Deploying Transformer models on edge devices is limited by latency and energy budgets. While INT8 quantization effectively accelerates the primary matrix multiplications, it exposes the softmax-related path as the domina…

Clustering-friendly Representation Learning via Instance Discrimination and Feature Decorrelation

2021-05-31 · ICLR 2021 1 · Yaling Tao, Kentaro Takagi, Kouta Nakata

Clustering is one of the most fundamental tasks in machine learning. Recently, deep clustering has become a major trend in clustering techniques. Representation learning often plays an important role in the effectiveness…

ClusteringDeep ClusteringImage ClusteringRepresentation Learning

Enhanced Isotropy Maximization Loss: Seamless and High-Performance Out-of-Distribution Detection Simply Replacing the SoftMax Loss

2021-05-30 · David Macêdo, Teresa Ludermir

Current out-of-distribution detection approaches usually present special requirements (e.g., collecting outlier data and hyperparameter validation) and produce side effects (e.g., classification accuracy drop and slow/in…

Out-of-Distribution Detection