<ul><li>FuncGNN is a proposed method to improve the representation of logic circuits using Graph Neural Networks (GNNs).</li><li>It addresses issues such as structural heterogeneity and global logic information loss in And-Inverter Graphs (AIGs) commonly used in electronic design automation.</li><li>FuncGNN integrates hybrid feature aggregation, gate-aware normalization, and multi-layer integration to enhance logic circuit representations.</li><li>Experimental results show that FuncGNN outperforms existing methods in logic-level analysis tasks while reducing training time and GPU memory usage.</li></ul>

FuncGNN: Learning Functional Semantics of Logic Circuits with Graph Neural Networks

Discover more