paper-with-me

Papers

Extensible Proxy for Efficient NAS

2022-10-17 · Yuhong Li, Jiajie Li, Cong Han, Pan Li, JinJun Xiong, Deming Chen

Neural Architecture Search (NAS) has become a de facto approach in the recent trend of AutoML to design deep neural networks (DNNs). Efficient or near-zero-cost NAS proxies are further proposed to address the demanding computational issues of NAS, where each candidate architecture network only requires one iteration of backpropagation. The values obtained from the proxies are considered the predictions of architecture performance on downstream tasks. However, two significant drawbacks hinder the extended usage of Efficient NAS proxies. (1) Efficient proxies are not adaptive to various search spaces. (2) Efficient proxies are not extensible to multi-modality downstream tasks. Based on the observations, we design a Extensible proxy (Eproxy) that utilizes self-supervised, few-shot training (i.e., 10 iterations of backpropagation) which yields near-zero costs. The key component that makes Eproxy efficient is an untrainable convolution layer termed barrier layer that add the non-linearities to the optimization spaces so that the Eproxy can discriminate the performance of architectures in the early stage. Furthermore, to make Eproxy adaptive to different downstream tasks/search spaces, we propose a Discrete Proxy Search (DPS) to find the optimized training settings for Eproxy with only handful of benchmarked architectures on the target tasks. Our extensive experiments confirm the effectiveness of both Eproxy and Eproxy+DPS. Code is available at https://github.com/leeyeehoo/GenNAS-Zero.

📄 PDF Abstract BibTeX arXiv:2210.09459

Code (1)

leeyeehoo/gennas-zero 공식 구현 pytorch

Tasks

AutoMLNeural Architecture Search

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Extensible and Efficient Proxy for Neural Architecture Search

2023-01-01 · ICCV 2023 1 · Yuhong Li, Jiajie Li, Cong Hao, Pan Li 외

Efficient or near-zero-cost proxies were proposed recently to address the demanding computational issues of Neural Architecture Search (NAS) in designing deep neural networks (DNNs), where each candidate architecture…

GPUNeural Architecture Search

MirrorBench: A Benchmark to Evaluate Conversational User-Proxy Agents for Human-Likeness

2026-01-13 · Ashutosh Hathidara, Julien Yu, Vaishali Senthil, Sebastian Schreiber 외 arxiv

Large language models (LLMs) are increasingly used as human simulators, both for evaluating conversational systems and for generating fine-tuning data. However, naive "act-as-a-user" prompting often yields verbose, unrea…

GSDeformer: Direct, Real-time and Extensible Cage-based Deformation for 3D Gaussian Splatting

2024-05-24 · Jiajun Huang, Shuolin Xu, Hongchuan Yu, Jian Jun Zhang 외

We present GSDeformer, a method that achieves cage-based deformation on 3D Gaussian Splatting (3DGS). Our method bridges cage-based deformation and 3DGS using a proxy point cloud representation. The point cloud is create…

3DGS

Multi-Agent Firewall Architecture for Privacy Protection of Sensitive Data in Interactions with Language Models

2026-07-09 · Hugo García Cuesta, Pablo Mateo Torrejón, Alfonso Sánchez-Macián arxiv

While Large Language Models (LLMs) have become essential productivity tools, their integration into workflows without adequate safeguards creates significant risks. This paper proposes an open-source, privacy-focused, us…

Extensible Embedding: A Flexible Multipler For LLM's Context Length

2024-02-18 · Ninglu Shao, Shitao Xiao, Zheng Liu, Peitian Zhang

Large language models (LLMs) call for extension of context to handle many critical applications. However, the existing approaches are prone to expensive costs and inferior quality of context extension. In this work, we p…

Language ModelingLanguage Modelling