# DeepGate4: Efficient and Effective Representation Learning for Circuit Design at Scale

arXiv: https://arxiv.org/abs/2502.01681 · HTML: https://mlsanity.com/paper/2502.01681/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 39 references that are in the map.
- First posted on arXiv 2 Feb 2025.

## Builds on (most cited first, 29 of 29)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks](https://mlsanity.com/paper/1711.02257/) (2017)
- [Recipe for a General, Powerful, Scalable Graph Transformer](https://mlsanity.com/paper/2205.12454/) (2022)
- [High Fidelity Neural Audio Compression](https://mlsanity.com/paper/2210.13438/) (2022)
- [On the Bottleneck of Graph Neural Networks and its Practical Implications](https://mlsanity.com/paper/2006.05205/) (2020)
- [Principal Neighbourhood Aggregation for Graph Nets](https://mlsanity.com/paper/2004.05718/) (2020)
- [Rethinking Graph Transformers with Spectral Attention](https://mlsanity.com/paper/2106.03893/) (2021)
- [A Survey on Oversmoothing in Graph Neural Networks](https://mlsanity.com/paper/2303.10993/) (2023)
- [NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification](https://mlsanity.com/paper/2306.08385/) (2023)
- [Exphormer: Sparse Transformers for Graphs](https://mlsanity.com/paper/2303.06147/) (2023)
- [GraphiT: Encoding Graph Structure in Transformers](https://mlsanity.com/paper/2106.05667/) (2021)
- [NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs](https://mlsanity.com/paper/2206.04910/) (2022)
- [GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings](https://mlsanity.com/paper/2106.05609/) (2021)
- [DeepGate: Learning Neural Representations of Logic Gates](https://mlsanity.com/paper/2111.14616/) (2021)
- [DeepGate2: Functionality-Aware Circuit Representation Learning](https://mlsanity.com/paper/2305.16373/) (2023)
- [GraphFM: Improving Large-Scale GNN Training via Feature Momentum](https://mlsanity.com/paper/2206.07161/) (2022)
- [OpenABC-D: A Large-Scale Dataset For Machine Learning Guided Integrated Circuit Synthesis](https://mlsanity.com/paper/2110.11292/) (2021)
- [Understanding GNN Computational Graph: A Coordinated Computation, IO, and Memory Perspective](https://mlsanity.com/paper/2110.09524/) (2021)
- [Gamora: Graph Learning based Symbolic Reasoning for Large-Scale Boolean Networks](https://mlsanity.com/paper/2303.08256/) (2023)
- [DeepGate3: Towards Scalable Circuit Representation Learning](https://mlsanity.com/paper/2407.11095/) (2024)
- [Transformers over Directed Acyclic Graphs](https://mlsanity.com/paper/2210.13148/) (2022)
- [Over-Squashing in Graph Neural Networks: A Comprehensive survey](https://mlsanity.com/paper/2308.15568/) (2023)
- [Sketch-GNN: Scalable Graph Neural Networks with Sublinear Training Complexity](https://mlsanity.com/paper/2406.15575/) (2024)
- [DeepSAT: An EDA-Driven Learning Framework for SAT](https://mlsanity.com/paper/2205.13745/) (2022)
- [DeepTPI: Test Point Insertion with Deep Reinforcement Learning](https://mlsanity.com/paper/2206.06975/) (2022)
- [DeepSeq: Deep Sequential Circuit Learning](https://mlsanity.com/paper/2302.13608/) (2023)
- [Logic Optimization Meets SAT: A Novel Framework for Circuit-SAT Solving](https://mlsanity.com/paper/2403.19446/) (2024)

## Built on by (most cited first, 12 of 12)

- [DeepCircuitX: A Comprehensive Repository-Level Dataset for RTL Code Understanding, Generation, and PPA Analysis](https://mlsanity.com/paper/2502.18297/) (2025)
- [MMCircuitEval: A Comprehensive Multimodal Circuit-Focused Benchmark for Evaluating LLMs](https://mlsanity.com/paper/2507.19525/) (2025)
- [BBOPlace-Bench: Benchmarking Black-Box Optimization for Chip Placement](https://mlsanity.com/paper/2510.23472/) (2025)
- [DeepCell: Self-Supervised Multiview Fusion for Circuit Representation Learning](https://mlsanity.com/paper/2502.06816/) (2025)
- [DICE: Device-level Integrated Circuits Encoder with Graph Contrastive Pretraining](https://mlsanity.com/paper/2502.08949/) (2025)
- [GenEDA: Towards Generative Netlist Functional Reasoning via Cross-Modal Circuit Encoder-Decoder Alignment](https://mlsanity.com/paper/2504.09485/) (2025)
- [Functional Matching of Logic Subgraphs: Beyond Structural Isomorphism](https://mlsanity.com/paper/2505.21988/) (2025)
- [Alignment Unlocks Complementarity: A Framework for Multiview Circuit Representation Learning](https://mlsanity.com/paper/2509.20968/) (2025)
- [Modeling Relational Logic Circuits for And-Inverter Graph Convolutional Network](https://mlsanity.com/paper/2508.11991/) (2025)
- [Learning Representations Through Contrastive Neural Model Checking](https://mlsanity.com/paper/2510.01853/) (2025)
- [KCLNet: Electrically Equivalence-Oriented Graph Representation Learning for Analog Circuits](https://mlsanity.com/paper/2603.24101/) (2026)
- [Natural Synthesis: Outperforming Reactive Synthesis Tools with Large Reasoning Models](https://mlsanity.com/paper/2605.15131/) (2026)

## Abstract (arXiv)

Circuit representation learning has become pivotal in electronic design automation, enabling critical tasks such as testability analysis, logic reasoning, power estimation, and SAT solving. However, existing models face significant challenges in scaling to large circuits due to limitations like over-squashing in graph neural networks and the quadratic complexity of transformer-based models. To address these issues, we introduce DeepGate4, a scalable and efficient graph transformer specifically designed for large-scale circuits. DeepGate4 incorporates several key innovations: (1) an update strategy tailored for circuit graphs, which reduce memory complexity to sub-linear and is adaptable to any graph transformer; (2) a GAT-based sparse transformer with global and local structural encodings for AIGs; and (3) an inference acceleration CUDA kernel that fully exploit the unique sparsity patterns of AIGs. Our extensive experiments on the ITC99 and EPFL benchmarks show that DeepGate4 significantly surpasses state-of-the-art methods, achieving 15.5% and 31.1% performance improvements over the next-best models. Furthermore, the Fused-DeepGate4 variant reduces runtime by 35.1% and memory usage by 46.8%, making it highly efficient for large-scale circuit analysis. These results demonstrate the potential of DeepGate4 to handle complex EDA tasks while offering superior scalability and efficiency. Code is available at https://github.com/zyzheng17/DeepGate4-ICLR-25.