EurekAlert!

Soft-GNN: towards robust graph neural networks via self-adaptive data utilization

Graph neural networks (GNNs) have gained traction and have been applied to various graph-based data analysis tasks due to their high performance. However, a major concern is their robustness, ...
EurekAlert!

Real-time, large-scale graph neural network inference through BingoCGN

BingoCGN employs cross-partition message quantization to summarize inter-partition message flow, which eliminates the need for irregular off-chip memory access and utilizes a fine-grained structured ...
Donga Science

Adaptive Semiconductor Resolves Bottleneck in AI Graph Data Processing

Graph Neural Networks (GNNs)' are an AI technology used to analyze complex relationships, such as those needed for YouTube video recommendations. A South Korean research team has developed a "transfo ...
Business Wire

New MLPerf Training Benchmark Results Highlight Hardware and Software Innovations in AI Systems

SAN FRANCISCO--(BUSINESS WIRE)--Today, MLCommons ® announced new results for the MLPerf ® Training v4.0 benchmark suite, including first-time results for two benchmarks: LoRA fine-tuning of LLama 2 ...
Semiconductor Engineering

GNN-Based Pre-Silicon Power Side-Channel Analysis Framework At RTL Level

A technical paper titled “SCAR: Power Side-Channel Analysis at RTL-Level” was published by researchers at University of Texas at Dallas, Technology Innovation Institute and University of Illinois ...
Semiconductor Engineering

GNN-Based Framework for Hardware Trojan Detection, Including RISC-V Cores

A new technical paper titled “TROJAN-GUARD: Hardware Trojans Detection Using GNN in RTL Designs” was published by researchers at University of Connecticut and University of Minnesota. “hip ...