Pith. sign in

REVIEW 26 cited by

Predict then Propagate: Graph Neural Networks meet Personalized PageRank

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 1810.05997 v6 pith:IFHGNZKW submitted 2018-10-14 cs.LG stat.ML

Johannes Gasteiger , Aleksandar Bojchevski , Stephan Günnemann This is my paper · ORCID
classification cs.LGstat.ML
keywords neuralpropagationclassificationmodelpagerankpersonalizedgraphmethods
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Neural message passing algorithms for semi-supervised classification on graphs have recently achieved great success. However, for classifying a node these methods only consider nodes that are a few propagation steps away and the size of this utilized neighborhood is hard to extend. In this paper, we use the relationship between graph convolutional networks (GCN) and PageRank to derive an improved propagation scheme based on personalized PageRank. We utilize this propagation procedure to construct a simple model, personalized propagation of neural predictions (PPNP), and its fast approximation, APPNP. Our model's training time is on par or faster and its number of parameters on par or lower than previous models. It leverages a large, adjustable neighborhood for classification and can be easily combined with any neural network. We show that this model outperforms several recently proposed methods for semi-supervised classification in the most thorough study done so far for GCN-like models. Our implementation is available online.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 26 Pith papers

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

  1. NodeImport: Imbalanced Node Classification with Node Importance Assessment

    cs.LG 2026-07 conditional novelty 6.0 of 10

    A closed-form importance score — the gradient alignment between a node and a balanced meta-set — filters labeled, unlabeled, and synthetic nodes, improving GNN balanced accuracy under class imbalance.

  2. Scalable Topology-Preserving Graph Coarsening: Concepts and Algorithms

    cs.LG 2026-01 conditional novelty 6.0 of 10

    STPGC coarsens graphs by iteratively removing dominated nodes and edges (plus a neighborhood-coning step), preserving clique-complex homotopy and yielding 8.7–37x speedups over GEC on large graphs.

  3. A Hierarchical Quantized Tokenization Framework for Task-Adaptive Graph Representation Learning

    cs.IR 2025-10 unverdicted novelty 6.0 of 10

    QUIET is a hierarchical RVQ-based graph tokenizer with a learned level-weighting gate; it improves several benchmarks but not consistently against the strongest baselines.

  4. ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs

    cs.LG 2025-07 conditional novelty 6.0 of 10

    ProGMLP trains a sequence of MLPs with progressive distillation and mixup, enabling flexible accuracy-speed trade-offs for graph node classification in one framework.

  5. When Speed meets Accuracy: an Efficient and Effective Graph Model for Temporal Link Prediction

    cs.AI 2025-07 conditional novelty 6.0 of 10

    EAGLE predicts temporal links with top-k recent neighbors plus top-k shared temporal PageRank influencers, matching or beating transformer T-GNNs while running far faster.

  6. It Takes a Graph to Know a Graph: Rewiring for Homophily with a Reference Graph

    cs.LG 2025-05 conditional novelty 6.0 of 10

    REFine rewires a graph toward a label-driven reference graph to increase edge homophily, and standard GNNs trained on the rewired graph match or beat specialized heterophilic GNNs on several benchmarks.

  7. Adaptive Branch Specialization in Spectral-Spatial Graph Neural Networks for Certified Robustness

    cs.LG 2025-05 reject novelty 6.0 of 10

    SpecSphere fuses an edge-robust spectral branch and a feature-robust spatial branch with a learnable gate, and claims certified robustness against both l0 edge flips and linf feature perturbations.

  8. Hierarchical Uncertainty-Aware Graph Neural Network

    cs.LG 2025-04 reject novelty 6.0 of 10

    An uncertainty-aware hierarchical GNN that reweights local, community, and global messages improves semi-supervised node classification on several homophilic and heterophilic benchmarks, though the theoretical bounds ...

  9. Semantica: Decentralized Search using a LLM-Guided Semantic Tree Overlay

    cs.IR 2025-02 conditional novelty 6.0 of 10

    A decentralized search overlay places users in a binary tree over LLM document embeddings with soft cloning and expansion rounds, retrieving more relevant documents than random or graph-diffusion baselines at equal ne...

  10. Spectro-Riemannian Graph Neural Networks

    cs.LG 2025-02 conditional novelty 6.0 of 10

    CUSP is a graph neural network that combines Ollivier-Ricci curvature with spectral filters on a product of hyperbolic, spherical, and Euclidean spaces, claiming SOTA results on eight node and link prediction benchmarks.

  11. MADE: Graph Backdoor Defense with Masked Unlearning

    cs.CR 2024-11 conditional novelty 6.0 of 10

    MADE is a training-set-only graph backdoor defense combining homophily-based poisoned-sample isolation with masked unlearning to drive attack success rate to near zero while keeping accuracy high.

  12. Personalized One-shot Federated Graph Learning for Heterogeneous Clients

    cs.LG 2024-11 conditional novelty 6.0 of 10

    O-pFGL achieves one-shot personalized federated graph learning by aggregating class-wise feature statistics into a surrogate graph and combining global distillation with local fine-tuning, outperforming baselines on 1...

  13. ProPRL: Property-Aware Prerequisite Relation Learning in Educational Knowledge Graphs

    cs.AI 2026-08 conditional novelty 5.0 of 10

    ProPRL improves prerequisite relation prediction by fusing resource and behavior graph views with a pair-adaptive gate and an anti-symmetry regularizer, achieving the best reported numbers on three benchmarks.

  14. GegenNet: Spectral Convolutional Neural Networks for Link Sign Prediction in Signed Bipartite Graphs

    cs.LG 2025-08 conditional novelty 5.0 of 10

    GegenNet predicts link signs in signed bipartite graphs with Gegenbauer-polynomial spectral filters on positive and negative edges, reporting up to 4.28% AUC and 11.69% F1 gains over 11 baselines.

  15. Uncertainty-Aware Graph Neural Networks: A Multi-Hop Evidence Fusion Approach

    cs.LG 2025-06 conditional novelty 5.0 of 10

    EFGNN fuses per-depth evidential opinions from a multi-hop GNN into one final Dirichlet-based prediction whose uncertainty is lower than that of any single propagation depth.

  16. LightKG: Efficient Knowledge-Aware Recommendations with Simplified GNN Architecture

    cs.IR 2025-06 conditional novelty 5.0 of 10

    LightKG, a simplified GNN recommender with scalar relation weights and an efficient contrastive loss, outperforms 12 knowledge-graph-aware baselines on four datasets, especially under sparse interactions, while cuttin...

  17. OpenGT: A Comprehensive Benchmark For Graph Transformers

    cs.LG 2025-06 conditional novelty 5.0 of 10

    OpenGT benchmarks 16 graph models on 14 datasets, finding graph transformers excel on heterophilous graphs, though several observations are not robustly supported.

  18. IceBerg: Debiased Self-Training for Class-Imbalanced Node Classification

    cs.LG 2025-02 conditional novelty 5.0 of 10

    IceBerg uses pseudo-label-based double balancing and decoupled propagation to improve graph neural networks on class-imbalanced and few-shot node classification.

  19. THeGCN: Temporal Heterophilic Graph Convolutional Network

    cs.LG 2024-12 conditional novelty 5.0 of 10

    THeGCN uses learned low/high-pass attention over sampled temporal events to improve semi-supervised node classification on event-based continuous graphs with both edge and temporal heterophily.

  20. Graph Coarsening via Supervised Granular-Ball for Scalable Graph Neural Network Training

    cs.LG 2024-12 reject novelty 5.0 of 10

    SGBGC compresses graphs by grouping same-label nodes into granular-balls and training GNNs on the coarsened graph, but its evaluation leaks test labels into the coarsening step.

  21. Scaling Up Graph Propagation Computation on Large Graphs: A Local Chebyshev Approximation Approach

    cs.LG 2024-12 conditional novelty 5.0 of 10

    Graph propagation queries can be accelerated by replacing Taylor expansions with Chebyshev polynomials, yielding a claimed O(sqrt(N)) reduction in iterations and a local push algorithm.

  22. Know Your Account: Double Graph Inference-based Account De-anonymization on Ethereum

    cs.SI 2024-11 conditional novelty 5.0 of 10

    A dual static-dynamic graph model with ECE-weighted confidence calibration classifies Ethereum account types and reports F1 scores above 97 percent.

  23. Unveiling the Inflexibility of Adaptive Embedding in Traffic Forecasting

    cs.LG 2024-11 conditional novelty 5.0 of 10

    Replacing learned adaptive node embeddings with PCA-derived embeddings keeps traffic forecasting models accurate across years and cities without retraining.

  24. Simplifying Graph Kernels for Efficient

    cs.LG 2025-07 conditional novelty 4.0 of 10

    SGTK and SGNK perform K-step graph aggregation before a single NTK or Gaussian process kernel update, yielding large speedups over GNTK with roughly competitive accuracy.

  25. AttriReBoost: A Gradient-Free Propagation Optimization Method for Cold Start Mitigation in Attribute Missing Graphs

    cs.LG 2025-01 conditional novelty 4.0 of 10

    AttriReBoost augments feature propagation with a partial reset of known nodes and a global-mean (virtual edge) term, achieving consistent but modest accuracy gains over FP and PCFI on eight benchmarks.

  26. Heterogeneous networks in drug-target interaction prediction

    q-bio.BM 2025-04 conditional novelty 1.0 of 10

    A review of graph-based and heterogeneous-network methods for drug-target interaction prediction published mostly between 2020 and 2024, with datasets, metrics, future challenges, and claimed source code links.

Pith tools