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
465 results for “keyword:"raph neural networks"” in ICLR 2027. 90 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Bridging the Completeness Gap in GraphRAG: A Unified GNN Enhancement Layer for Retrieval and Generation▲2.0k1.50
[PDF]From Art to Engineering: An Architecture Evaluation Framework for Edge-Level Deep Graph Transformation▲11.00
[PDF]From Values to Interactions: Adaptive Graph Pre-training for Spatiotemporal Forecasting▼1611.50
[PDF]Who Gets to Constrain the Decision? Authority-Conditioned Graph Fusion for Clinical Multimodal Learning▼4.5k2.67
[PDF]Uncertainty is not Enough: Misclassification Detection via Distribution-aware Bayesian Graph Neural Networks▲1.8k1.33
[PDF]A Unified Framework for EEG–Video Emotion Recognition with Brain Anatomy and Temporal Priors▼4.3k2.00
[PDF]G3I-Net: A Trimodal Architecture for Tumor Staging and How Much Its Gene Graphs Actually Vary▼4.3k2.00
[PDF]ECHO: A Hybrid Neural Operator For Coupled Thermo-Hydro-Mechanical Modelling In Enhanced Geothermal Systems▼1361.33
[PDF]Hidden Equivalences in Sheaf Neural Networks: The Share Credited to Matrix-Valued Transport Is Not Intrinsic▲1.7k3.33
[PDF]LEMON: Equivariant Learning over Attention Maps for Zero-Shot Misbehavior Monitoring on New LLMs▲5103.00
[PDF]GCMatch: Protein Pocket Matching with Geometric–Chemical Spatial Semantic Modeling and Fine-Grained Representations▲3952.67
[PDF]Learning to Decompose and Act: Landmark-Based Manager–Worker Policies for Generalized Planning at Scale▲3952.67
[PDF]Stealth Still Leaves Traces: Exposing and Reducing Trigger Footprints in Graph Backdoor Attacks▼4.3k2.00
[PDF]KU-GAD: Rethinking Semi-Supervised Graph Anomaly Detection with Known–Unlabeled Discrimination▲5103.00
[PDF]Invariant Structural Distillation via Graph Condensation for History-Aware Graph Continual Learning▲9.2k2.67
[PDF]The Score Is Not the Model: Four Protocol Failure Modes in Open Graph Benchmark Reporting▼1.2k1.67
[PDF]CalibHyper: Chance-Corrected Relational Hypergraphs for Few-Shot Molecular Property Prediction▲1.7k3.33
Withdrawn or desk rejected (90)
[PDF]Same-Checkpoint Intervention on Pre- and Post-Context States in Entity-Local Temporal EncodersWithdrawn1.33
[PDF]Graphs are Evidence, Not CircuitsDesk rejected
[PDF]Learning Around Analytical Solutions: Risk-Calibrated Corrections for Sparse Graph SensingWithdrawn1.00
[PDF]Boundary-Condition Compliance in Learned Fluid Simulators: Boundary Particles over Distance Features and the Primacy of Geometric FidelityDesk rejected
[PDF]Hybrid Parallelism for GPU-Accelerated Representation Learning on Geospatial and Graph-Structured DataDesk rejected