Pith. sign in

REVIEW 7 cited by

Graph HyperNetworks for Neural Architecture Search

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1810.05749 v3 pith:B5PDOSOK submitted 2018-10-12 cs.LG cs.CVstat.ML

Chris Zhang , Mengye Ren , Raquel Urtasun This is my paper
classification cs.LGcs.CVstat.ML
keywords searcharchitectureneuralghnsgraphnetworknetworksdesigns
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Neural architecture search (NAS) automatically finds the best task-specific neural network topology, outperforming many manual architecture designs. However, it can be prohibitively expensive as the search requires training thousands of different networks, while each can last for hours. In this work, we propose the Graph HyperNetwork (GHN) to amortize the search cost: given an architecture, it directly generates the weights by running inference on a graph neural network. GHNs model the topology of an architecture and therefore can predict network performance more accurately than regular hypernetworks and premature early stopping. To perform NAS, we randomly sample architectures and use the validation accuracy of networks with GHN generated weights as the surrogate search signal. GHNs are fast -- they can search nearly 10 times faster than other random search methods on CIFAR-10 and ImageNet. GHNs can be further extended to the anytime prediction setting, where they have found networks with better speed-accuracy tradeoff than the state-of-the-art manual designs.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. NN-Former: Rethinking Graph Structure in Neural Architecture Representation

    cs.LG 2025-07 conditional novelty 6.0 of 10

    NN-Former improves neural accuracy and latency prediction by using attention masks over sibling nodes in the architecture graph.

  2. Projectable Models: One-Shot Generation of Small Specialized Transformers from Large Ones

    cs.LG 2025-06 conditional novelty 6.0 of 10

    A task-conditioned projection operator converts a large transformer's weights into a smaller task-specialized transformer that outperforms same-size universal conditional models.

  3. Examining the Efficacy of Graph Neural Network Message-Passing in Regression Contexts

    cs.LG 2026-07 conditional novelty 5.0 of 10

    Across four NAS/DNN-predictor regression benchmarks, GEN (deep graph convolution) achieves the best average rank over 11 GNN message-passing layers, though attention GATv2 wins on the largest graphs.

  4. SBS: Enhancing Parameter-Efficiency of Neural Representations for Neural Networks via Spectral Bias Suppression

    cs.LG 2025-09 conditional novelty 5.0 of 10

    SBS improves NeRN weight compression by unidirectional kernel smoothing and RFF bandwidth that shrinks for larger networks, cutting required MLP parameters by roughly 2 to 3 times.

  5. Ada-TransGNN: An Air Quality Prediction Model Based On Adaptive Graph Convolutional Networks

    cs.LG 2025-08 conditional novelty 5.0 of 10

    Ada-TransGNN predicts air quality indices with a Transformer-graph hybrid that learns the station graph adaptively and uses a Moran-coefficient auxiliary task.

  6. Text-to-LoRA: Instant Transformer Adaption

    cs.LG 2025-06 conditional novelty 5.0 of 10

    A hypernetwork can generate task-specific LoRA adapters from a text description, and when trained with supervised fine-tuning it zero-shot outperforms a multi-task LoRA baseline on ten benchmarks.

  7. Compressed Learning for Nanosurface Deficiency Recognition Using Angle-resolved Scatterometry Data

    eess.SP 2025-08 unverdicted novelty 4.0 of 10

    A compressed learning framework claims to classify five levels of deficiency in ZnO nanosurfaces from 1 to 6 percent of angle-resolved scatterometry samples, with 86 to 94 percent accuracy.

Pith tools