mlsanityData to 14 Oct 2026

DeepGate3: Towards Scalable Circuit Representation Learning

arXiv 2407.11095 ↗First posted 15 Jul 2024cs.LG cs.AIcited by 26

Not on the map. Why?

Abstract (arXiv)

Circuit representation learning has shown promising results in advancing the field of Electronic Design Automation (EDA). Existing models, such as DeepGate Family, primarily utilize Graph Neural Networks (GNNs) to encode circuit netlists into gate-level embeddings. However, the scalability of GNN-based models is fundamentally constrained by architectural limitations, impacting their ability to generalize across diverse and complex circuit designs. To address these challenges, we introduce DeepGate3, an enhanced architecture that integrates Transformer modules following the initial GNN processing. This novel architecture not only retains the robust gate-level representation capabilities of its predecessor, DeepGate2, but also enhances them with the ability to model subcircuits through a novel pooling transformer mechanism. DeepGate3 is further refined with multiple innovative supervision tasks, significantly enhancing its learning process and enabling superior representation of both gate-level and subcircuit structures. Our experiments demonstrate marked improvements in scalability and generalizability over traditional GNN-based approaches, establishing a significant step forward in circuit representation learning technology.

Key facts. Cited by 26 papers in the map (data through 14 Oct 2026). Builds on 28 of its 53 references that are in the map. First posted on arXiv 15 Jul 2024.

Builds on

28 of 53 references.

References · 28

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  5. 2017Graph Attention Networkscited by 8,923
  6. 2020Scaling Laws for Neural Language Modelscited by 6,586
  7. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  8. 2018How Powerful are Graph Neural Networks?cited by 4,393
  9. 2019Generating Long Sequences with Sparse Transformerscited by 1,546
  10. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,102
  11. 2021Scaling Vision Transformerscited by 999
  12. 2020Efficient Transformers: A Surveycited by 790
16 more
  1. 2020On the Bottleneck of Graph Neural Networks and its Practical Implicationscited by 631
  2. 2022InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutionscited by 482
  3. 2021Understanding over-squashing and bottlenecks on graphs via curvaturecited by 478
  4. 2023Scaling Data-Constrained Language Modelscited by 403
  5. 2019Blockwise Self-Attention for Long Document Understandingcited by 159
  6. 2022Revisiting Neural Scaling Laws in Language and Visioncited by 132
  7. 2022Benchmarking Large Language Models for Automated Verilog RTL Code Generationcited by 115
  8. 2024OpenGraph: Towards Open Graph Foundation Modelscited by 78
  9. 2022Data Scaling Laws in NMT: The Effect of Noise and Architecturecited by 55
  10. 2021DeepGate: Learning Neural Representations of Logic Gatescited by 37
  11. 2023DeepGate2: Functionality-Aware Circuit Representation Learningcited by 33
  12. 2023Gamora: Graph Learning based Symbolic Reasoning for Large-Scale Boolean Networkscited by 27
  13. 2022PACE: A Parallelizable Computation Encoder for Directed Acyclic Graphscited by 20
  14. 2022DeepSAT: An EDA-Driven Learning Framework for SATcited by 11
  15. 2022DeepTPI: Test Point Insertion with Deep Reinforcement Learningcited by 10
  16. 2023DeepSeq: Deep Sequential Circuit Learningcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 19; 2026: 7.

26 papers.

Sort:

By area:

  1. 2025DeepCircuitX: A Comprehensive Repository-Level Dataset for RTL Code Understanding, Generation, and PPA Analysiscited by 21
  2. 2025DeepGate4: Efficient and Effective Representation Learning for Circuit Design at Scalecited by 12
  3. 2025NetTAG: A Multimodal RTL-and-Layout-Aligned Netlist Foundation Model via Text-Attributed Graphcited by 9
  4. 2025Revolution or Hype? Seeking the Limits of Large Models in Hardware Designcited by 9
  5. 2025Circuit Representation Learning with Masked Gate Modeling and Verilog-AIG Alignmentcited by 8
  6. 2025MMCircuitEval: A Comprehensive Multimodal Circuit-Focused Benchmark for Evaluating LLMscited by 6
  7. 2025DeepCell: Self-Supervised Multiview Fusion for Circuit Representation Learningcited by 3
  8. 2025DICE: Device-level Integrated Circuits Encoder with Graph Contrastive Pretrainingcited by 2
  9. 2025Circuit-Aware SAT Solving: Guiding CDCL via Conditional Probabilitiescited by 2
  10. 2025GenEDA: Towards Generative Netlist Functional Reasoning via Cross-Modal Circuit Encoder-Decoder Alignmentcited by 1
  11. 2025Functional Matching of Logic Subgraphs: Beyond Structural Isomorphismcited by 1
  12. 2025FuncGNN: Learning Functional Semantics of Logic Circuits with Graph Neural Networkscited by 1
14 more
  1. 2025Alignment Unlocks Complementarity: A Framework for Multiview Circuit Representation Learningcited by 1
  2. 2026R2G: A Multi-View Circuit Graph Benchmark Suite from RTL to GDSIIcited by 1
  3. 2025Modeling Relational Logic Circuits for And-Inverter Graph Convolutional Networkcited by 0
  4. 2025TRACE: Learning to Compute on Circuit Graphscited by 0
  5. 2025Learning Representations Through Contrastive Neural Model Checkingcited by 0
  6. 2025BoolSkeleton: Boolean Network Skeletonization via Homogeneous Pattern Reductioncited by 0
  7. 2025InF-ATPG: Intelligent FFR-Driven ATPG with Advanced Circuit Representation Guided Reinforcement Learningcited by 0
  8. 2025ReVEAL: GNN-Guided Reverse Engineering for Formal Verification of Optimized Multiplierscited by 0
  9. 2026GNN-based Path-aware multi-view Circuit Learning for Technology Mappingcited by 0
  10. 2026Wrong Code, Right Structure: Learning Netlist Representations from Imperfect LLM-Generated RTLcited by 0
  11. 2026KCLNet: Electrically Equivalence-Oriented Graph Representation Learning for Analog Circuitscited by 0
  12. 2026Graph Computation Meets Circuit Algebra: A Task-Aligned Analysis of Graph Neural Networks for Electronic Design Automationcited by 0
  13. 2026Beyond Flat Netlist: Hierarchical Graph Representation Learning for Scalable Analysis of Sequential Circuitscited by 0
  14. 2026ReDIL-GNN: Resynthesis Domain Incremental Learning for Circuit Graph Neural Networkscited by 0