arXiv AI
When Missingness Follows the Graph: Beyond Feature Propagation for Missing Features
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Jul 13
Pattern-Aware Graph Neural Networks for Handling Missing Data
arXiv:2607. 08915v1 Announce Type: new Abstract: Missing data is ubiquitous in real-world datasets.
arXiv Machine Learning
Sep 29
Robust Graph Clustering Network for Multiple Missing Data
The paper introduces the Robust Graph Clustering Network for Multiple Missing Data (RGCN), a method designed to cluster graphs with simultaneous missing node attributes and structural links. RGCN employs a view‑decoupled dual‑branch imputation to reduce cross‑view interference, a multi‑hyperspherical mixture prior to improve cluster compactness and separability on a directional latent manifold, and a boundary‑aware contrastive enhancement objective to counteract cluster blurring caused by imputation bias. Experiments on real‑world datasets show that RGCN consistently outperforms state‑of‑the‑art baselines across various missing data patterns.
arXiv AI
Oct 15
Learning Higher-Order Interactions from Incomplete Spatiotemporal Data with Mixtures of Hypergraph Laplacians
The paper introduces MoHL, a mixture of hypergraph Laplacians that learns group-wise relational structure directly from incomplete spatiotemporal traffic sensor data. MoHL discovers overlapping sensor groups, constructs a Laplacian component for each interaction order, and learns their mixture through holdouts that mimic missingness patterns, sharing weights across group-induced couplings to pool evidence. Experiments on three traffic networks show that MoHL achieves the lowest error under day-long gaps, with far fewer learned parameters than deep imputers, demonstrating the benefit of higher-order groups and shared weights when relational evidence is scarce.
arXiv Machine Learning
4d ago
Diagnosing GNN Failure Modes with Layer-Wise Probe Entropy
The paper introduces a post-hoc diagnostic for graph neural networks that freezes a trained model, fits a linear probe to each layer, and tracks probe accuracy with normalized predictive entropy. By examining layer-wise probe entropy, the authors can distinguish beneficial, neutral, and harmful smoothing effects—something existing geometric measures cannot do. The study also shows that entropy degradation patterns separate two main GNN failure modes: structural mismatch under heterophily, which appears early even in shallow models, and excessive-depth oversmoothing that emerges only as propagation depth increases.
arXiv Machine Learning
Jun 8
Spatiotemporal Imputation with Graph-Informed Flow Matching
arXiv:2606. 06682v1 Announce Type: new Abstract: Missing data is a common challenge in spatiotemporal systems, arising in applications such as air quality monitoring and urban traffic management.
arXiv AI
Sep 30
ProCTI: Prototype-Refined Global Conditioning for Diffusion-Based Time Series Imputation
arXiv:2609.37632v1 Announce Type: cross Abstract: Time series imputation has progressed from statistical and deep learning approaches to diffusion-based models, which have shown strong recent perform...