TopGQ: Fast GNN Post-Training Quantization Leveraging Topology Information

TopGQ: Fast GNN Post-Training Quantization Leveraging Topology Information

TopGQ is a post‑training graph neural network (GNN) quantization framework that reduces quantization overhead by using dual‑axis scale absorption, which merges one dimension into the adjacency matrix for activation quantization. It also introduces TopPIN, a proxy for nodes’ local structure, to group nodes with similar topology during quantization. Experiments demonstrate that TopGQ cuts quantization time by an order of magnitude while maintaining accuracy.

Generalizing GNNs with Tokenized Mixture of Experts

arXiv:2602. 09258v2 Announce Type: replace Abstract: Deployed graph neural networks (GNNs) are frozen at deployment yet must fit clean data, generalize under distribution shifts, and remain stable to perturbations.

Quanto: a PyTorch quantization backend for Optimum

eCNNTO: A Highly Generalizable ConvNet for Accelerating Topology Optimization

arXiv:2606. 19921v1 Announce Type: new Abstract: This work proposes an element-based Convolutional Neural Network (CNN) to accelerate density-based Topology Optimization (TO), termed eCNNTO.

HOPSE: Scalable Higher-Order Positional and Structural Encoder for Combinatorial Representations

arXiv:2505. 15405v3 Announce Type: replace Abstract: While Graph Neural Networks (GNNs) have proven highly effective at modeling relational data, pairwise connections cannot fully capture multi-way relationships naturally present in complex real-world systems.

MiCoPro: End-to-End Mixed Precision HW/SW Co-design with HW-aware Proxy Model

arXiv:2608. 06916v1 Announce Type: new Abstract: Quantized Neural Networks~(QNN) with low-bitwidth data have proven promising in efficient storage and computation on edge devices.