TopGQ, an accurate post-training GNN quantization framework, alleviating redundant quantization overhead, is presented, and dual-axis scale absorption is proposed, which enables activation quantization along both the outer and inner dimensions by merging one into the adjacency matrix.
Abstract
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-training GNN quantization framework, alleviating redundant quantization overhead. We propose dual-axis scale absorption, which enables activation quantization along both the outer and inner dimensions by merging one into the adjacency matrix. On top of that, we introduce TopPIN, a proxy for nodes'local structure, and use it to group nodes with similar topology during quantization. Experimental results show that TopGQ reduces quantization time by an order of magnitude while preserving accuracy.
In indirect quantization tasks, the quantize-thenestimate (QE) scheme is commonly adopted when encoders are distributed or task-agnostic. In some scenarios, however, the observation dimension substantially exceeds that of the underlying state, rendering direct quantization of the observations highly inefficient. In thi...
A target-centric survey of QAT is provided, aimed at clarifying both its theoretical foundations and its evolving implementation landscape and synthesizing cross-target differences in error characteristics, numerical formats, and strategy transferability.
Jiashun Song, Mengjie Zhao, Zi-Jing Wang et al.· 0 citations
Real-Q (Real-time E2E-loss Aligned LLM Quantization), a novel PTQ paradigm that breaks this compromise: instead of diluting the objective for the sake of analytic tractability, REAL-Q targets an end-to-end-aligned surrogate of the global loss and refines it via fine-grained, dynamic Block-wise Gradient Descent applied...
Qian Zhang, Yao-Ming Li, Zheng Tan et al.· 0 citations
The Noise Equivalent Hypothesis is proposed: the noise inherent to the weight quantization process plays a role functionally analogous to the stochastic gradient variance present in standard SGD optimization, and it is theoretically prove that just as a decaying learning rate is essential for convergence, an ascending...
Hong Huang, Jia-Xun Ye, Jin-Hai Yang et al.· Proceedings of the 32nd ACM...· 0 citations
A cross-modal structural sensitivity asymmetry in VLMs is revealed and SeGO is proposed, a unified structural sensitivity-aware sparse optimization framework that achieves the balance among model parameter amount, quantization accuracy and scaling factors’ search efficiency on InternVL2 and LLaVA series.
Tian-Qi Zhao, Xin-Rui Cheng, Yang Su et al.· Proceedings of the Thirty-Fi...· 0 citations
OCGQuant is proposed, a post-training quantization method centered on Outlier-Companion Grouping (OCG), which adaptively pairs outlier channels with low-magnitude companion channels to improve NVFP4 activation block composition.
Yi-Shan Yao, Bin-Jun Li, Han-Ling Yi et al.· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduOct 13, 2026
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
MIT News · Artificial Intelligence· news.mit.eduSep 29, 2026
Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.
