{"ID":2855511,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.12094","arxiv_id":"2510.12094","title":"H4G: Unlocking Faithful Inference for Zero-Shot Graph Learning in Hyperbolic Space","abstract":"Text-attributed graphs are widely used across domains, offering rich opportunities for zero-shot learning via graph-text alignment. However, existing methods struggle with tasks requiring fine-grained pattern recognition, particularly on heterophilic graphs. Through empirical and theoretical analysis, we identify an \\textbf{over-abstraction problem}: current approaches operate at excessively large hyperbolic radii, compressing multi-scale structural information into uniform high-level abstractions. This abstraction-induced information loss obscures critical local patterns essential for accurate predictions. By analyzing embeddings in hyperbolic space, we demonstrate that optimal graph learning requires \\textbf{faithful preservation} of fine-grained structural details, better retained by representations positioned closer to the origin. To address this, we propose \\textbf{H4G}, a framework that systematically reduces embedding radii using learnable block-diagonal scaling matrices and Möbius matrix multiplication. This approach restores access to fine-grained patterns while maintaining global receptive ability with minimal computational overhead. Experiments show H4G achieves state-of-the-art zero-shot performance with \\textbf{12.8\\%} improvement on heterophilic graphs and \\textbf{8.4\\%} on homophilic graphs, confirming that radius reduction enables faithful multi-scale representation for advancing zero-shot graph learning.","short_abstract":"Text-attributed graphs are widely used across domains, offering rich opportunities for zero-shot learning via graph-text alignment. However, existing methods struggle with tasks requiring fine-grained pattern recognition, particularly on heterophilic graphs. Through empirical and theoretical analysis, we identify an \\t...","url_abs":"https://arxiv.org/abs/2510.12094","url_pdf":"https://arxiv.org/pdf/2510.12094v1","authors":"[\"Heng Zhang\",\"Tianyi Zhang\",\"Zijun Liu\",\"Yuling Shi\",\"Yaomin Shen\",\"Haochen You\",\"Haichuan Hu\",\"Lubin Gan\",\"Jin Huang\"]","published":"2025-10-14T02:58:57Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.GR\"]","methods":"[]","has_code":false}