Jiahao Xie, Guangmo Tong · ACM International Conference on Information and Knowledge Management (CIKM) 2026 · 2026
DOI: 10.48550/arxiv.2608.21825
Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).
Learning adjacency matrices from node-link images is a fundamental problem for recovering structured graph information from visual observations.Existing methods typically rely on fixed KNN-based heuristics for candidate edge selection and fail to capture dependencies among edges.To overcome these limitations, we propose VisAdj, a new framework for topology-aware adjacency prediction. VisAdj introduces an attention-sparse neighbor sampler to adaptively select a high-recall set of candidate node pairs and performs joint edge inference using a line-graph transformer that treats candidate edges as tokens and explicitly models dependencies among incident edges.Extensive experiments on synthetic graphs, road networks, and vessel images demonstrate that VisAdj consistently outperforms existing baselines by clear margins.
No comments yet — start the discussion below.