Neural Architecture Performance Prediction

Latest papers

13 papers4 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Searching with Sparse Histories: Cross-Task Architecture Search from Incomplete Search Logs and Zero-Cost Proxies
Oct 23, 2026Yuefeng Xu, Jun YuNeural Architecture Performance Prediction Neural Architecture Search
Graduate School of Science and Technology, Niigata University, Niigata, Japan · Institute of Science and Technology, Niigata University, Niigata, Japan
Neural Spectral Capacity with Residual Context for Heterogeneous Resource Allocation within Transformers
Oct 22, 2026Chenyu Zhu, Ruoyu Zhao, Zhichao LuNeural Architecture Performance Prediction Neural Architecture Search
Department of Computer Science, City University of Hong Kong
DTA-GT: Direction- and Topology-Aware Graph Transformer for Neural Network Representation Learning
Oct 12, 2026Yuxiang Zeng, Kun Xie, Yang Wang +5Neural Architecture Performance Prediction Graph Transformer
Hunan University · Hunan University of Science and Technology · Chinese Academy of Sciences +1
Prediction-powered Neural Architecture Search
Oct 1, 2026Pascal Janetzky, Yuxin Wang, Michael Klar +1Neural Architecture Search Prediction-Powered Inference
Bosch Center for Artificial Intelligence · LMU Munich Munich Center for Machine Learning(MCML)
Neural Spectral Capacity: Measuring and Designing Architectures from Network Specification Alone
Sep 19, 2026Chenyu Zhu, Ruoyu Zhao, Zhichao LuNeural Architecture Performance Prediction Neural Architecture Search
Department of Computer Science, City University of Hong Kong
RiPPLE: Cross-Space Performance Prediction from Early Training for Neural Architecture Search
Sep 11, 2026Yifan Yang, Zhaoyan Wang, Zheng Gao +2Learning to Rank Neural Architecture Performance Prediction
University of New South Wales · Korea Advanced Institute of Science and Technology
Node-wise Feature Encoding for Neural Performance Prediction
Aug 28, 2026Matthew Grenier, William Hammer, Andrew Heuer +3Neural Architecture Performance Prediction Energy-Efficient ML
University of South Carolina Department of Computer Science and Engineering · University of South Carolina Department of Mechanical Engineering
InTrain: Intrinsic Trainability for Zero-Cost Neural Architecture Search
Jun 17, 2026Qinqin Zhou, Fuhai Chen, Jipeng Wu +3Neural Architecture Search Neural Architecture Performance Prediction
School of Computer and Data Science, Fuzhou University · School of Computer and Data Science, Minjiang University · School of Artificial Intelligence, Nanchang University +2
Towards Code-Oriented LM Embeddings for Surrogate-Assisted Neural Architecture Search
May 15, 2026Pranav Somu, Advay Balakrishnan, Stepan Kravtsov +2Neural Surrogate Modeling Representation Learning
Georgia Institute of Technology Atlanta, Georgia, USA · Georgia Tech Research Institute Atlanta, Georgia, USA
From Regression to Inference: Meta-Learning Predictors for Neural Architecture Search
May 10, 2026Liping Deng, MingQing XiaoNeural Surrogate Modeling Meta-Learning
Department of Mathematics University of California, Riverside Riverside, CA 92507 USA · School of Mathematical and Statistical Sciences Southern Illinois University Carbondale Carbondale, IL 62901 USA
From Code to Prediction: Fine-Tuning LLMs for Neural Network Performance Classification in NNGPT
May 5, 2026Mahmoud Hanouneh, Radu Timofte, Dmitry IgnatovLLM Fine-Tuning Automated Machine Learning
Computer Vision Lab, CAIDAS & IFI, University of Würzburg, Germany
Fast and Generalizable NeRF Architecture Selection for Satellite Scene Reconstruction
Mar 18, 2026Devjyoti Chakraborty, Zaki Sukma, Rakandhiya D. Rachmanto +6Neural Architecture Performance Prediction Neural Radiance Fields
School of Computing, University of Georgia · Department of Geography, University of Georgia
SEval-NAS: A Search-Agnostic Evaluation for Neural Architecture Search
Feb 17, 2026Atah Nuh Mih, Jianzhou Wang, Truong Thanh Hung Nguyen +1Neural Architecture Performance Prediction Neural Architecture Search
Analytics Everywhere Lab, University of New Brunswick, Canada

Oct 23, 2026J/K move · Enter open · S save

Searching with Sparse Histories: Cross-Task Architecture Search from Incomplete Search Logs and Zero-Cost Proxies

Yuefeng Xu, Jun Yu

Graduate School of Science and Technology, Niigata University, Niigata, Japan · Institute of Science and Technology, Niigata University, Niigata, Japan

Neural Architecture Performance Prediction Neural Architecture Search

Open paper AskPDF arXiv

Neural architecture search (NAS) is expensive, but cross-task transfer can reduce costs by reusing knowledge from previous tasks. However, existing methods struggle with sparse search histories and task-specific transfer failures. We propose a method, a risk-robust strategy that combines sparse source logs with zero-cost proxies through champion-based initialization and joint pairwise-ranker pretraining. On TransNAS-Bench-101, the proposal mitigates severe worst-case failures, reducing worst-10% ranks from 290 to 43 for Micro autoencoding and from 465 to 45 for Macro room layout. Across 13 cell-space targets, it outperforms a proxy-only ranker on 10 targets in both mean and worst-case performance, while maintaining competitive average performance.