A Benchmark on Directed Graph Representation Learning in Hardware Designs

2024-10-09 · Haoyu Wang, Yinan Huang, Nan Wu, Pan Li

To keep pace with the rapid advancements in design complexity within modern computing systems, directed graph representation learning (DGRL) has become crucial, particularly for encoding circuit netlists, computational graphs, and developing surrogate models for hardware performance prediction. However, DGRL remains relatively unexplored, especially in the hardware domain, mainly due to the lack of comprehensive and user-friendly benchmarks. This study presents a novel benchmark comprising five hardware design datasets and 13 prediction tasks spanning various levels of circuit abstraction. We evaluate 21 DGRL models, employing diverse graph neural networks and graph transformers (GTs) as backbones, enhanced by positional encodings (PEs) tailored for directed graphs. Our results highlight that bidirected (BI) message passing neural networks (MPNNs) and robust PEs significantly enhance model performance. Notably, the top-performing models include PE-enhanced GTs interleaved with BI-MPNN layers and BI-Graph Isomorphism Network, both surpassing baselines across the 13 tasks. Additionally, our investigation into out-of-distribution (OOD) performance emphasizes the urgent need to improve OOD generalization in DGRL models. This benchmark, implemented with a modular codebase, streamlines the evaluation of DGRL models for both hardware and ML practitioners

📄 PDF Abstract BibTeX arXiv:2410.06460

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Representation Learning Representation Learning

Methods 이 논문이 사용한 방법론

GTS 설명 없음

Optimising Graph Representation for Hardware Implementation of Graph Convolutional Networks for Event-based Vision

2024-01-10 · Kamil Jeziorek, Piotr Wzorek, Krzysztof Blachut, Andrea Pinna 외

Event-based vision is an emerging research field involving processing data generated by Dynamic Vision Sensors (neuromorphic cameras). One of the latest proposals in this area are Graph Convolutional Networks (GCNs), whi…

Event-based vision Graph Generation object-detection Object Detection

Towards Data-centric Machine Learning on Directed Graphs: a Survey

2024-11-28 · Henan Sun, Xunkai Li, Daohan Su, Junyi Han 외

In recent years, Graph Neural Networks (GNNs) have made significant advances in processing structured data. However, most of them primarily adopted a model-centric approach, which simplifies graphs by converting them int…

Graph Learning Model Optimization Survey

Learning Semantic Representations to Verify Hardware Designs

2021-12-01 · NeurIPS 2021 12 · Shobha Vasudevan, Wenjie (Joe) Jiang, David Bieber, Rishabh Singh 외

Verification is a serious bottleneck in the industrial hardware design cycle, routinely requiring person-years of effort. Practical verification relies on a "best effort" process that simulates the design on test inputs.…

Graph Neural Network Learning Semantic Representations

EvolveGen: Algorithmic Level Hardware Model Checking Benchmark Generation through Reinforcement Learning

2026-02-26 · Guangyu Hu, Xiaofeng Zhou, Wei Zhang, Hongce Zhang arxiv

Progress in hardware model checking depends critically on high-quality benchmarks. However, the community faces a significant benchmark gap: existing suites are limited in number, often distributed only in representation…

Reinforcement Learning

Agentic evolution of physically constrained foundation models

2026-06-24 · Jiangwei Zhang, Wen Sun, Chong Wang, Shiyao Li 외 arxiv

Artificial intelligence increasingly drives automated scientific discovery, yet contemporary generalist agents lack physical grounding, frequently hallucinating hardware-incompatible designs. Here, we present a physicall…