paper-with-me

Papers

AutoReP: Automatic ReLU Replacement for Fast Private Network Inference

2023-08-20 · ICCV 2023 1 · Hongwu Peng, Shaoyi Huang, Tong Zhou, Yukui Luo, Chenghong Wang, Zigeng Wang, Jiahui Zhao, Xi Xie, Ang Li, Tony Geng, Kaleel Mahmood, Wujie Wen, Xiaolin Xu, Caiwen Ding

The growth of the Machine-Learning-As-A-Service (MLaaS) market has highlighted clients' data privacy and security issues. Private inference (PI) techniques using cryptographic primitives offer a solution but often have high computation and communication costs, particularly with non-linear operators like ReLU. Many attempts to reduce ReLU operations exist, but they may need heuristic threshold selection or cause substantial accuracy loss. This work introduces AutoReP, a gradient-based approach to lessen non-linear operators and alleviate these issues. It automates the selection of ReLU and polynomial functions to speed up PI applications and introduces distribution-aware polynomial approximation (DaPa) to maintain model expressivity while accurately approximating ReLUs. Our experimental results demonstrate significant accuracy improvements of 6.12% (94.31%, 12.9K ReLU budget, CIFAR-10), 8.39% (74.92%, 12.9K ReLU budget, CIFAR-100), and 9.45% (63.69%, 55K ReLU budget, Tiny-ImageNet) over current state-of-the-art methods, e.g., SNL. Morever, AutoReP is applied to EfficientNet-B2 on ImageNet dataset, and achieved 75.55% accuracy with 176.1 times ReLU budget reduction.

📄 PDF Abstract BibTeX arXiv:2308.10134

Code (1)

harveyp123/autorep 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

AutoReproduce: Automatic AI Experiment Reproduction with Paper Lineage

2025-05-27 · Xuanle Zhao, Zilin Sang, YuXuan Li, Qi Shi 외

Efficient experiment reproduction is critical to accelerating progress in artificial intelligence. However, the inherent complexity of method design and training procedures presents substantial challenges for automation.…

Decision-Aware Quadratic ReLU Replacement for HE-Friendly Inference

2026-05-21 · Rui Li, Wenyuan Wu, Weijie Miao arxiv

Fully homomorphic encryption (FHE) supports only additions and multiplications, so FHE-only neural-network inference typically replaces ReLU with polynomials fitted over empirical activation intervals. Such interval fitt…

DeepReDuce: ReLU Reduction for Fast Private Inference

2021-03-02 · Nandan Kumar Jha, Zahra Ghodsi, Siddharth Garg, Brandon Reagen

The recent rise of privacy concerns has led researchers to devise methods for private neural inference -- where inferences are made directly on encrypted data, never seeing inputs. The primary challenge facing private in…

Repairing dynamic models: a method to obtain identifiable and observable reparameterizations with mechanistic insights

2020-12-17 · Gemma Massonis, Julio R. Banga, Alejandro F. Villaverde

Mechanistic dynamic models allow for a quantitative and systematic interpretation of data and the generation of testable hypotheses. However, these models are often over-parameterized, leading to non-identifiability and …

AutoReply: Detecting Nonsense in Dialogue Introspectively with Discriminative Replies

2022-11-22 · Weiyan Shi, Emily Dinan, Adi Renduchintala, Daniel Fried 외

Existing approaches built separate classifiers to detect nonsense in dialogues. In this paper, we show that without external classifiers, dialogue models can detect errors in their own messages introspectively, by calcul…