Pith. sign in

REVIEW 22 cited by

Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2009.03509 v5 pith:6DK6VFSA submitted 2020-09-08 cs.LG stat.ML

Yunsheng Shi , Zhengjie Huang , Shikun Feng , Hui Zhong , Wenjin Wang , Yu Sun This is my paper
classification cs.LGstat.ML
keywords labelpropagationfeaturegraphnetworkunimpclassificationinformation
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Graph neural network (GNN) and label propagation algorithm (LPA) are both message passing algorithms, which have achieved superior performance in semi-supervised classification. GNN performs feature propagation by a neural network to make predictions, while LPA uses label propagation across graph adjacency matrix to get results. However, there is still no effective way to directly combine these two kinds of algorithms. To address this issue, we propose a novel Unified Message Passaging Model (UniMP) that can incorporate feature and label propagation at both training and inference time. First, UniMP adopts a Graph Transformer network, taking feature embedding and label embedding as input information for propagation. Second, to train the network without overfitting in self-loop input label information, UniMP introduces a masked label prediction strategy, in which some percentage of input label information are masked at random, and then predicted. UniMP conceptually unifies feature propagation and label propagation and is empirically powerful. It obtains new state-of-the-art semi-supervised classification results in Open Graph Benchmark (OGB).

Discussion (0). Sign in to comment.

Forward citations

Cited by 22 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. LAEF: A Lead-Agnostic ECG Foundation Model Towards Point-of-Care Diagnostics

    cs.LG 2026-08 conditional novelty 7.0 of 10

    A 7M-parameter graph ECG foundation model pre-trained with random lead dropout matches 12-lead models on full input and beats zero-padded baselines on most datasets with 1-2 leads.

  2. Gaussian Sheaf Neural Networks

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    Gaussian Sheaf Neural Networks derive a sheaf Laplacian for Gaussian node features on graphs to preserve their geometric structure during message passing.

  3. How Attentive are Graph Attention Networks?

    cs.LG 2021-05 conditional novelty 7.0 of 10

    GAT uses static attention where neighbor rankings ignore the query node and thus cannot express some graph problems; GATv2 enables dynamic attention and outperforms GAT on 11 OGB and other benchmarks with equal parameters.

  4. Graph Neural Network-based Algorithm Selection for the Traveling Salesman Problem: A Systematic Study of Cost and Rank Losses under Distinct Budget Regimes

    cs.LG 2026-07 conditional novelty 6.0 of 10

    GNNAS-TSP, a GNN-based TSP algorithm selector, improves normalized solution cost over the single best solver at 10s and 60s budgets, with the 10s gain post-hoc significant.

  5. Parameter-Free Encoders Remain Viable for RDB Foundation Models

    cs.LG 2026-07 accept novelty 6.0 of 10

    Trainable RDB encoders cannot robustly exploit neighborhood labels as fixed foundation-model features or feature-importance signals, so simple parameter-free encoders stay near-SOTA.

  6. RelPrism: A Multi-Faceted Pre-training Framework with Self-Generated Tasks for Relational Databases

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    RelPrism generates self-supervised pseudo-tasks from three attribute perspectives via multi-granularity clustering to improve representation learning for relational database prediction tasks.

  7. KoRe: Compact Knowledge Representations for Large Language Models

    cs.CL 2026-05 unverdicted novelty 6.0 of 10

    KoRe encodes 1-hop knowledge graph subgraphs as compact discrete tokens for injection into LLMs, achieving competitive benchmark performance with up to 10x token reduction.

  8. KoRe: Compact Knowledge Representations for Large Language Models

    cs.CL 2026-05 conditional novelty 6.0 of 10

    KoRe compresses one-hop knowledge-graph subgraphs into 20 discrete tokens that, injected into Qwen3-8B, match or beat text-based knowledge injection on three QA benchmarks while using up to 10x fewer tokens.

  9. Attention Enhanced Entity Recommendation for Intelligent Monitoring in Cloud Systems

    cs.LG 2025-10 conditional novelty 6.0 of 10

    A heterogeneous-graph recommender with multi-head attention, random-walk attention, and an alignment loss recommends cloud-monitor dimensions, beating baseline GNNs on Microsoft's production data and on DBLP/LastFM.

  10. Asynchronous Cooperative Multi-Agent Reinforcement Learning with Limited Communication

    cs.MA 2025-02 unverdicted novelty 6.0 of 10

    AsynCoMARL is a new asynchronous MARL algorithm that matches leading baselines on success and collision rates while using 26% fewer messages via graph transformers on dynamic communication graphs.

  11. Domain-Prior-Regularized Graph Modeling for Anomaly Detection in Cyber-Physical Systems

    cs.LG 2026-07 conditional novelty 5.0 of 10

    A forecasting-based anomaly detector whose sensor graph is hard-gated by an LLM-extracted physical-coupling prior and modulated by Pearson correlations outperforms several baselines on SKAB.

  12. Parameter-Free Encoders Remain Viable for RDB Foundation Models

    cs.LG 2026-07 conditional novelty 5.0 of 10

    A parameter-free relational encoder combined with a single-table foundation model matches or beats parameterized, pre-trained RDB encoders on six benchmarks.

  13. Geometry-Aware Superpixel Graph Transformer with Metadata for Skin Lesion Classification

    cs.CV 2026-06 unverdicted novelty 5.0 of 10

    A superpixel graph transformer encodes lesion geometry and metadata in a unified relational structure and reports improved benign-malignant classification on four public benchmarks.

  14. Graph Transfer Learning via Shared Latent Geometry: Theory and Applications

    cs.LG 2026-05 unverdicted novelty 5.0 of 10

    An asymmetric two-pathway graph neural network architecture enables certified zero-shot transfer of inference across changing system topologies by anchoring latent geometry to operator spectra.

  15. On Efficient Scaling of GNNs via IO-Aware Layers Implementations

    cs.LG 2026-05 unverdicted novelty 5.0 of 10

    IO-aware GPU kernels for SpMM convolutions, degree-aware reductions, and fused attention layers deliver median speedups of 1.6-2.6x (up to 10x) and memory reductions up to 76x over DGL/PyG baselines on realistic graphs.

  16. Softsign: Smooth Sign in Your Optimizer For Better Parameter Heterogeneity Handling

    cs.LG 2026-05 unverdicted novelty 5.0 of 10

    SoftSignum replaces hard sign with soft-sign in optimizers via temperature control and quantile scheduling, extends to SoftMuon, provides a convergence proof for stochastic non-convex settings, and reports better perf...

  17. Physics-Informed Graph Neural Network Surrogates for Turbulent Nanoparticle Dispersion in Dental Clinical Environments

    cs.LG 2026-05 unverdicted novelty 5.0 of 10

    ELGIN is a graph-based physics-informed surrogate model that predicts carrier flow and polydisperse particle motion in dental aerosol scenarios, achieving lower tracking errors and 37x speedup versus full OpenFOAM CFD...

  18. PLMGH: What Matters in PLM-GNN Hybrids for Code Classification and Vulnerability Detection

    cs.SE 2026-04 unverdicted novelty 5.0 of 10

    Controlled experiments show PLM-GNN hybrids improve code tasks over GNN-only baselines, with PLM source having larger impact than GNN backbone.

  19. Distributed Control of Network Systems in the Space of Stabilizing Graph Neural Network Policies

    eess.SY 2025-12 conditional novelty 5.0 of 10

    A graph-neural-network policy parameterization guarantees closed-loop stability by construction and transfers from small to large networks without retraining.

  20. A Spatio-Temporal Graph Neural Networks Approach for Predicting Silent Data Corruption inducing Circuit-Level Faults

    cs.LG 2025-09 conditional novelty 5.0 of 10

    An ST-GCN predicts multi-cycle fault impact probabilities in sequential circuits from graph structure and temporal features, cutting analysis time versus full fault simulation, though the key validation is partly circular.

  21. Query-Aware Learnable Graph Pooling Tokens as Prompt for Large Language Models

    cs.CL 2025-01 unverdicted novelty 5.0 of 10

    LGPT and Early Query Fusion create flexible graph representations for LLMs, achieving 4.13% improvement on GraphQA without training the model.

  22. Enhancing a high resolution data-driven weather prediction model with surface descriptors

    physics.ao-ph 2026-07 conditional novelty 4.5 of 10

    Surface descriptors cut 2 m temperature and 10 m wind MAE by 1.9% and 3.0% domain-wide (about 12% for urban temperature) in a stretched-grid data-driven weather model, and glacier removal raises temperature without re...

Pith tools