REVIEW 9 cited by
Predict then Propagate: Graph Neural Networks meet Personalized PageRank
Not yet reviewed by Pith; the record is open.
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
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.
Forward citations
Cited by 9 Pith papers
-
NodeImport: Imbalanced Node Classification with Node Importance Assessment
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.
-
Scalable Topology-Preserving Graph Coarsening: Concepts and Algorithms
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.
-
A Hierarchical Quantized Tokenization Framework for Task-Adaptive Graph Representation Learning
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.
-
When Speed meets Accuracy: an Efficient and Effective Graph Model for Temporal Link Prediction
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.
-
GegenNet: Spectral Convolutional Neural Networks for Link Sign Prediction in Signed Bipartite Graphs
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.
-
Uncertainty-Aware Graph Neural Networks: A Multi-Hop Evidence Fusion Approach
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.
-
LightKG: Efficient Knowledge-Aware Recommendations with Simplified GNN Architecture
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...
-
OpenGT: A Comprehensive Benchmark For Graph Transformers
OpenGT benchmarks 16 graph models on 14 datasets, finding graph transformers excel on heterophilous graphs, though several observations are not robustly supported.
-
Simplifying Graph Kernels for Efficient
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.
Discussion (0). Sign in to comment.