mlsanityData to 7 Oct 2026

Graph Computation Meets Circuit Algebra: A Task-Aligned Analysis of Graph Neural Networks for Electronic Design Automation

arXiv 2605.08291 ↗First posted 8 May 2026cs.LG cs.AI cs.ARcited by 0

Not on the map. Why?

Abstract (arXiv)

EDA problems are graph-structured, but not all graph-structured problems call for the same GNN computation. We argue that successful GNN-for-EDA methods are those whose propagation, aggregation, and supervision align with the native algebra of the target task. Concretely: static timing analysis is a max-plus/min-plus recurrence on a topologically ordered DAG, structurally aligned with asynchronous DAG-GNNs; placement is governed by hypergraph wirelength and density penalties and is exploited by differentiable placers rather than by message-passing GNNs alone; routing congestion is a sparse demand-supply field over a layout grid; switching-activity propagation is a probabilistic recurrence on a directed netlist; IR drop is a linear system on the power-delivery network; and analog symmetry extraction is a discrete constraint-prediction problem on schematic graphs. Through these task-by-task alignments we (i) review the GNN architectural toolkit relevant to circuits, (ii) formalize how circuit graphs differ from generic graphs (directed, heterogeneous, multi-scale, with sequential and clock structure), (iii) characterize where current methods succeed and where the algebra-architecture mismatch limits them, and (iv) identify failure modes--stage leakage, proxy-to-signoff gap, calibration, and design-distribution shift--that we believe are likely to dominate the next phase of work. We position the paper as a GNN-for-EDA, task-aligned analysis rather than a comprehensive AI-for-chip-design survey. Continuous SE(3)-equivariant geometric GNNs are usually mismatched to Manhattan digital layout, and LLM-for-RTL, HLS, and RL/diffusion-based topology generation are outside our scope.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 61 of its 91 references that are in the map. First posted on arXiv 8 May 2026.

Builds on

61 of 91 references.

References · 61

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2018How Powerful are Graph Neural Networks?cited by 4,355
  5. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  6. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  7. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  8. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  9. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
  10. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
  11. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
  12. 2021E(n) Equivariant Graph Neural Networkscited by 951
38 more
  1. 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 875
  2. 2020Simple and Deep Graph Convolutional Networkscited by 857
  3. 2021How Attentive are Graph Attention Networks?cited by 818
  4. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 786
  5. 2022Recipe for a General, Powerful, Scalable Graph Transformercited by 702
  6. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 679
  7. 2020On the Bottleneck of Graph Neural Networks and its Practical Implicationscited by 624
  8. 2020Heterogeneous Graph Transformercited by 581
  9. 2017SchNet: A continuous-filter convolutional neural network for modeling quantum interactionscited by 569
  10. 2018Hypergraph Neural Networkscited by 482
  11. 2021Understanding over-squashing and bottlenecks on graphs via curvaturecited by 471
  12. 2022MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fieldscited by 467
  13. 2019Self-Attention Graph Poolingcited by 421
  14. 2019Provably Powerful Graph Networkscited by 385
  15. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 368
  16. 2019Exact Combinatorial Optimization with Graph Convolutional Neural Networkscited by 313
  17. 2019PairNorm: Tackling Oversmoothing in GNNscited by 297
  18. 2023One for All: Towards Training One Graph Model for All Classification Taskscited by 239
  19. 2023NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classificationcited by 207
  20. 2023EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representationscited by 201
  21. 2023ChipNeMo: Domain-Adapted LLMs for Chip Designcited by 168
  22. 2023Exphormer: Sparse Transformers for Graphscited by 166
  23. 2021GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networkscited by 147
  24. 2022Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphscited by 144
  25. 2023SGFormer: Simplifying and Empowering Transformers for Large-Graph Representationscited by 131
  26. 2019D-VAE: A Variational Autoencoder for Directed Acyclic Graphscited by 98
  27. 2021Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classificationcited by 79
  28. 2021Machine Learning for Electronic Design Automation: A Surveycited by 71
  29. 2021Directed Acyclic Graph Neural Networkscited by 70
  30. 2024Polynormer: Polynomial-Expressive Graph Transformer in Linear Timecited by 64
  31. 2021Topology-Imbalance Learning for Semi-Supervised Node Classificationcited by 56
  32. 2023CktGNN: Circuit Graph Neural Network for Electronic Design Automationcited by 55
  33. 2024A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challengescited by 54
  34. 2024AnyGraph: Graph Foundation Model in the Wildcited by 51
  35. 2023ChiPFormer: Transferable Chip Placement via Offline Decision Transformercited by 42
  36. 2021DeepGate: Learning Neural Representations of Logic Gatescited by 37
  37. 2023DeepGate2: Functionality-Aware Circuit Representation Learningcited by 33
  38. 2023Gamora: Graph Learning based Symbolic Reasoning for Large-Scale Boolean Networkscited by 27

50 most cited of 61 All 61 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025DeepGate4: Efficient and Effective Representation Learning for Circuit Design at Scale
  2. 2025Graph Neural Networks Based Analog Circuit Link Prediction
  3. 2026CircuitReason-1k: Benchmarking Long-Horizon Visual-to-Symbolic Reasoning inElectrical Circuits
  4. 2026Complexity Horizons of Compressed Models in Analog Circuit Analysis
  5. 2024AnalogXpert: Automating Analog Topology Synthesis by Incorporating Circuit Design Expertise into Large Language Models
  6. 2026ARCS: Autoregressive Circuit Synthesis with Topology-Aware Graph Attention and Spec Conditioning
  7. 2025TopoSizing: An LLM-aided Framework of Topology-based Understanding and Sizing for AMS Circuits
  8. 2026PhysEDA: Physics-Aware Learning Framework for Efficient EDA With Manhattan Distance Decay