NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
796 results for “area:"learning on graphs and other geometries & topologies"” in ICLR 2027. 153 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]GraphSieve: Graph Purification via Attack-Agnostic Calibration across Perturbation Severities▼4.3k2.00
[PDF]Rethinking Learning-Based Influence Maximization: Simple Neural Surrogates and Native Discrete Search▲3.9k1.67
[PDF]Root Multiplicity Sets the Finite-Width Edge of Chaos in MLPs and Message-Passing Networks▼5.8k2.33
[PDF]MoDANet: A Motif-Aware Distance-Masked Attention Network for Molecular Property Prediction▲1.7k3.33
[PDF]Beyond Homogeneous Rules: Ontology-Aware Logical Reasoning for Temporal Knowledge Graphs▼5.8k2.33
[PDF]Your Temporal Link Predictor Is Blind to Who Is Active: A Missing Factor That Transfers Across Models▼1.1k3.25
[PDF]Euler Frequency Modulation for Non-Stationary Spatiotemporal Graph Traffic Forecasting▼1.2k1.67
[PDF]Bridging the Gap to Unseen Graphs: Target-Side Adaptation for Frozen Graph Foundation Models▼4.3k2.00
[PDF]GeoSlice-MGN: Analysis-Guided Geometric Routing for Impact Response Prediction in Realistic Structures▲5.4k3.00
[PDF]AURORA: Separating Angular Alignment from Radial Ordering in Hyperbolic Vision–Language Models▲3942.67
[PDF]Exposing Local Vulnerabilities in Neural Routing Solvers with an Efficient Black-Box Attack▲3942.67
Withdrawn or desk rejected (153)
[PDF]Mind Your Marginals: What Governs Fidelity in Linearized Hierarchical Optimal Transport?Desk rejected1.00
[PDF]From Euclidean to Riemannian: Boundary-Aware Geodesic Oversampling for Class-Imbalanced GraphsWithdrawn2.00
[PDF]Caustic Spectroscopy: Identifiability and Acquisition Limits of Topological Event TimingWithdrawn2.00
[PDF]Graphs are Evidence, Not CircuitsDesk rejected