arXiv AI September 1, 2026 By Dain Kwon, Kanghyun Choi, Hyeyoon Lee, Sunjong Park, Seoyong Lee, Sukjin Kim, Jinho Lee

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

efficiency

Hugging Face Trending Papers

Aug 31

TopGQ: Fast GNN Post-Training Quantization Leveraging Topology Information

Existing GNN quantization methods suffer from considerable quantization overhead, which severely limits their practical usage in real-world scenarios. To this end, we present TopGQ, an accurate post-t...

efficiency

arXiv Machine Learning

Jun 15

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.

By Xiaoguang Guo, Zehong Wang, Jiazheng Li, Shawn Spitzel, Qi Yang, Kaize Ding, Jundong Li, Chuxu Zhang

efficiency benchmarks

arXiv Machine Learning

Jun 5

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.

By Guillermo Bern\'ardez, Marco Montagna, Louis Van Langendonck, Martin Carrasco, Amirreza Akbari, Louisa Cornelis, Mathilde Papillon, Pere Barlet-Ros, Nina Miolane, Lev Telyatnikov

benchmarks

arXiv Machine Learning

Jul 31

TopoFormer: Topology Meets Attention for Graph Learning

arXiv:2607. 28259v1 Announce Type: new Abstract: We introduce Topoformer, a lightweight and scalable framework for graph representation learning that encodes topological structure into attention-friendly sequences.

By Md Joshem Uddin, Astrit Tola, Cuneyt Gurcan Akcora, Baris Coskunuzer

llms rag benchmarks

arXiv AI

Jun 19

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.

By Shengbiao Lu, Xiaodong Wei

arXiv AI

Sep 16

Repurposing Unified Topological Signatures for Graph Representation Learning

arXiv:2609.17061v1 Announce Type: cross Abstract: Message-passing Graph Neural Networks (GNNs) iteratively propagate and aggregate local neighborhood information followed by global readout to learn g...

By Sanyam Sanjay Jain, Anshika Krishnatray, Aditya Sharma, Vinti Agarwal

rag benchmarks

One email a morning, machine-written

Related stories

TopGQ: Fast GNN Post-Training Quantization Leveraging Topology Information

Generalizing GNNs with Tokenized Mixture of Experts

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

TopoFormer: Topology Meets Attention for Graph Learning

eCNNTO: A Highly Generalizable ConvNet for Accelerating Topology Optimization

Repurposing Unified Topological Signatures for Graph Representation Learning