paper-with-me

홈 › Papers

NASGEM: Neural Architecture Search via Graph Embedding Method

2020-07-08 · Hsin-Pai Cheng, Tunhou Zhang, Yixing Zhang, Shi-Yu Li, Feng Liang, Feng Yan, Meng Li, Vikas Chandra, Hai Li, Yiran Chen

Neural Architecture Search (NAS) automates and prospers the design of neural networks. Estimator-based NAS has been proposed recently to model the relationship between architectures and their performance to enable scalable and flexible search. However, existing estimator-based methods encode the architecture into a latent space without considering graph similarity. Ignoring graph similarity in node-based search space may induce a large inconsistency between similar graphs and their distance in the continuous encoding space, leading to inaccurate encoding representation and/or reduced representation capacity that can yield sub-optimal search results. To preserve graph correlation information in encoding, we propose NASGEM which stands for Neural Architecture Search via Graph Embedding Method. NASGEM is driven by a novel graph embedding method equipped with similarity measures to capture the graph topology information. By precisely estimating the graph distance and using an auxiliary Weisfeiler-Lehman kernel to guide the encoding, NASGEM can utilize additional structural information to get more accurate graph representation to improve the search efficiency. GEMNet, a set of networks discovered by NASGEM, consistently outperforms networks crafted by existing search methods in classification tasks, i.e., with 0.4%-3.6% higher accuracy while having 11%- 21% fewer Multiply-Accumulates. We further transfer GEMNet for COCO object detection. In both one-stage and twostage detectors, our GEMNet surpasses its manually-crafted and automatically-searched counterparts.

📄 PDF Abstract BibTeX arXiv:2007.04452

Code (0)

등록된 구현이 없습니다.

Tasks

Graph EmbeddingGraph SimilarityNeural Architecture Searchobject-detectionObject Detection

Similar Papers 제목 키워드 기반

Smooth Variational Graph Embeddings for Efficient Neural Architecture Search

2020-10-09 · Jovita Lukasik, David Friede, Arber Zela, Frank Hutter 외

Neural architecture search (NAS) has recently been addressed from various directions, including discrete, sampling-based methods and efficient differentiable approaches. While the former are notoriously expensive, the la…

AutoMLBayesian OptimizationGraph Neural NetworkNeural Architecture Search

Graph Neural Architecture Search with GPT-4

2023-09-30 · Haishuai Wang, Yang Gao, Xin Zheng, Peng Zhang 외

Graph Neural Architecture Search (GNAS) has shown promising results in automatically designing graph neural networks. However, GNAS still requires intensive human labor with rich domain knowledge to design the search spa…

Neural Architecture Search

Arch-Graph: Acyclic Architecture Relation Predictor for Task-Transferable Neural Architecture Search

2022-04-12 · CVPR 2022 1 · Minbin Huang, Zhijian Huang, Changlin Li, Xin Chen 외

Neural Architecture Search (NAS) aims to find efficient models for multiple tasks. Beyond seeking solutions for a single task, there are surging interests in transferring network design knowledge across multiple tasks. I…

Neural Architecture SearchRelation

Interstellar: Searching Recurrent Architecture for Knowledge Graph Embedding

2019-11-17 · NeurIPS 2020 12 · Yongqi Zhang, Quanming Yao, Lei Chen

Knowledge graph (KG) embedding is well-known in learning representations of KGs. Many models have been proposed to learn the interactions between entities and relations of the triplets. However, long-term information amo…

Graph EmbeddingKnowledge Graph EmbeddingNeural Architecture Search

Brain Graph Super-Resolution Using Adversarial Graph Neural Network with Application to Functional Brain Connectivity

2021-05-02 · Megi Isallari, Islem Rekik

Brain image analysis has advanced substantially in recent years with the proliferation of neuroimaging datasets acquired at different resolutions. While research on brain image super-resolution has undergone a rapid deve…

Graph EmbeddingGraph Neural NetworkImage Super-ResolutionSuper-Resolution