Pith. sign in

REVIEW 41 cited by

Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networks

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 2007.02901 v2 pith:UOYPRO74 submitted 2020-07-06 cs.LG cs.SIstat.ML

Péter Mernyei , Cătălina Cangea This is my paper
classification cs.LGcs.SIstat.ML
keywords datasetbenchmarkdifferentexperimentsgraphnetworksneuralwiki-cs
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We present Wiki-CS, a novel dataset derived from Wikipedia for benchmarking Graph Neural Networks. The dataset consists of nodes corresponding to Computer Science articles, with edges based on hyperlinks and 10 classes representing different branches of the field. We use the dataset to evaluate semi-supervised node classification and single-relation link prediction models. Our experiments show that these methods perform well on a new domain, with structural properties different from earlier benchmarks. The dataset is publicly available, along with the implementation of the data pipeline and the benchmark experiments, at https://github.com/pmernyei/wiki-cs-dataset .

Discussion (0). Sign in to comment.

Forward citations

Cited by 41 Pith papers

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

  1. PromptGNN-sim: Deep Fusion and Alignment of GNN and LLMs for Text-Attributed Graph Learning

    cs.AI 2026-06 unverdicted novelty 7.0 of 10

    PromptGNN-sim uses GAT-based semantically aware neighborhood selection and structure-aware LLM prompts with bi-directional contrastive alignment to outperform prior GNN, LLM, and fusion methods on text-attributed grap...

  2. TaLK: Text-attributed Graph Dataset Distillation via Coupling Language Model with Graph-Aware Kernel

    cs.LG 2026-06 unverdicted novelty 7.0 of 10

    TaLK distills TAG datasets via LM coupled with graph-aware NTK, outperforming baselines and reaching up to 97% full-dataset performance with 1% synthetic data.

  3. GraphInfer-Bench: Benchmarking LLM's Inference Capability on Graphs

    cs.LG 2026-06 unverdicted novelty 7.0 of 10

    Presents GraphInfer-Bench to demonstrate that no evaluated LLM-based method family closes the performance gap on graph inference tasks requiring multi-node reasoning, with plain GNNs matching or exceeding them.

  4. GFFMERGE: Efficient Merging of Graph Neural Force Fields and Beyond

    cs.LG 2026-06 unverdicted novelty 7.0 of 10

    GFFMERGE formulates GNN force field merging as a convex embedding-alignment problem with an analytical solution, recovering near joint-training performance on MD17, MD22, LiPS20 and other benchmarks while delivering 5...

  5. Neighbourhood Transformer: Switchable Attention for Monophily-Aware Graph Learning

    cs.LG 2026-04 unverdicted novelty 7.0 of 10

    Neighbourhood Transformers apply local self-attention for monophily-aware graph learning, guarantee expressiveness at least as strong as message-passing GNNs, and outperform prior methods on node classification across...

  6. Beyond One-Size-Fits-All: Adaptive Subgraph Denoising for Zero-Shot Graph Learning with Large Language Models

    cs.LG 2026-03 unverdicted novelty 7.0 of 10

    GraphSSR introduces an adaptive SSR pipeline with SSR-SFT data synthesis and SSR-RL (Authenticity-Reinforced and Denoising-Reinforced stages) to overcome one-size-fits-all subgraph noise in zero-shot LLM graph reasoning.

  7. Energy-Balanced Hyperspherical Graph Representation Learning via Structural Binding and Entropic Dispersion

    cs.LG 2025-12 unverdicted novelty 7.0 of 10

    HyperGRL places graph nodes on a hypersphere and minimizes Helmholtz free energy with structural binding energy and mean-field repulsive potential, regulated by an adaptive thermostat, to produce discriminative repres...

  8. When LLM Agents Meet Graph Optimization: An Automated Data Quality Improvement Approach

    cs.LG 2025-10 unverdicted novelty 7.0 of 10

    LAGA is a unified multi-agent LLM framework that automates comprehensive quality optimization for text-attributed graphs by running detection, planning, action, and evaluation agents in a closed loop.

  9. GILT: An LLM-Free, Tuning-Free Graph Foundational Model for In-Context Learning

    cs.LG 2025-10 unverdicted novelty 7.0 of 10

    GILT introduces a token-based in-context learning framework that unifies node, edge, and graph classification on heterogeneous graphs with numerical features, achieving tuning-free adaptation and stronger few-shot res...

  10. Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization

    cs.LG 2026-07 conditional novelty 6.0 of 10

    GNN weights trained on geometric-renormalization replicas of graphs transfer zero-shot to the original graph with largely preserved accuracy.

  11. Convex--Concave Quadratic Spectral Filtering for Graph Neural Networks

    cs.LG 2026-06 unverdicted novelty 6.0 of 10

    DCQ-GNN uses node-adaptive convex-concave quadratic spectral filters to boost selectivity and robustness in GNNs, ranking competitively on heterophilic and homophilic graphs with less degradation under perturbations.

  12. Graph Reduction in Multirelational Networks: A Spreading-Oriented Reduction Benchmark

    cs.SI 2026-06 unverdicted novelty 6.0 of 10

    Introduces the SORB benchmark showing that sparsification and coarsening effects on influence maximization performance depend strongly on network type and evaluation metric.

  13. GraspLLM: Towards Zero-Shot Generalization on Text-Attributed Graphs with LLMs

    cs.CL 2026-06 unverdicted novelty 6.0 of 10

    GraspLLM extracts dataset-agnostic structural patterns via motif contrastive learning and aligns contextual subgraphs to LLM tokens, outperforming prior LLM-based methods on TAGs especially in zero-shot settings.

  14. Beyond the Golden Teacher: Enhancing Graph Learning through LLM-GNN Co-teaching

    cs.LG 2026-06 unverdicted novelty 6.0 of 10

    Bidirectional LLM-GNN co-teaching with round-based pseudo-label preference optimization outperforms golden-teacher baselines on few-shot TAG benchmarks by 3-8% absolute gains.

  15. Generalizing Graph Foundation Models via Hyperbolic Retrieval-Augmented Generation

    cs.IR 2026-06 unverdicted novelty 6.0 of 10

    HyRAG improves zero-shot generalization of graph foundation models by indexing and retrieving from tree-structured knowledge in hyperbolic space via multi-granularity retrieval and dual-path fusion.

  16. Where LLM Annotators Fail: Label-Free Learning on Graphs with LLMs

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    CANE estimates cluster-specific reliability of noisy LLM pseudo-labels on graphs without ground truth to improve label-free node classification.

  17. S2Aligner: Pair-Efficient and Transferable Pre-Training for Sparse Text-Attributed Graphs

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    S2Aligner decouples semantic and structural components in LLM-as-Aligner pre-training for sparse TAGs and uses structure-oriented reconstruction plus domain risk balancing to improve transferability and reduce general...

  18. UFO: A Unified Flow-Oriented Framework for Robust Continual Graph Learning

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    UFO combines flow-based generative replay with instance-level reliability scoring to handle both catastrophic forgetting and catastrophic remembering from noisy supervision in evolving graphs, outperforming baselines ...

  19. Revisiting Graph-Tokenizing Large Language Models: A Systematic Evaluation of Graph Token Understanding

    cs.CL 2026-05 unverdicted novelty 6.0 of 10

    GTokenLLMs do not fully understand graph tokens, exhibiting over-sensitivity or insensitivity to instruction changes and relying heavily on text for reasoning even when graph information is preserved.

  20. Improving Graph Few-shot Learning with Hyperbolic Space and Denoising Diffusion

    cs.LG 2026-04 unverdicted novelty 6.0 of 10

    IMPRESS improves graph few-shot learning by learning representations in hyperbolic space and using denoising diffusion to better approximate target distributions from few support samples.

  21. DuConTE: Dual-Granularity Text Encoder with Topology-Constrained Attention for Text-attributed Graphs

    cs.CL 2026-04 unverdicted novelty 6.0 of 10

    DuConTE is a dual-granularity text encoder that incorporates graph topology into language model attention for improved node representations in text-attributed graphs.

  22. Disentangle-then-Refine: LLM-Guided Decoupling and Structure-Aware Refinement for Graph Contrastive Learning

    cs.AI 2026-04 unverdicted novelty 6.0 of 10

    SDM-SCR uses LLMs for semantic disentanglement of signal from noise in text-attributed graphs followed by spectral consistency regularization to improve contrastive learning performance.

  23. Toward a universal foundation model for graph-structured data

    cs.LG 2026-04 unverdicted novelty 6.0 of 10

    A pretrained graph model using feature-agnostic structural prompts matches or exceeds supervised baselines and shows strong zero-shot and few-shot transfer on held-out biomedical graphs, with a 21.8% ROC-AUC gain on SagePPI.

  24. Both Topology and Text Matter: Revisiting LLM-guided Out-of-Distribution Detection on Text-attributed Graphs

    cs.LG 2026-02 conditional novelty 6.0 of 10

    LG-Plug mines pseudo-OOD exposures from clustered unlabeled nodes via iterative LLM prompting and regularizes topology-driven graph OOD detectors, cutting FPR95 by ≥7% across six TAG benchmarks.

  25. Rethinking Federated Graph Foundation Models: A Graph-Language Alignment-based Approach

    cs.LG 2026-01 conditional novelty 6.0 of 10

    FedGALA replaces vector-quantized federated graph foundation models with continuous graph-text contrastive alignment plus prompt tuning, claiming up to 14.37% gains over 22 baselines.

  26. Fixed Aggregation Features Can Rival GNNs

    cs.LG 2026-01 conditional novelty 6.0 of 10

    Fixed, untrained neighborhood statistics fed into a well-tuned MLP match or outperform classic GNNs on 12 of 14 node-classification benchmarks.

  27. GILT: An LLM-Free, Tuning-Free Graph Foundational Model for In-Context Learning

    cs.LG 2025-10 conditional novelty 6.0 of 10

    GILT turns few-shot node, edge, and graph classification into a token-reasoning problem and reaches competitive accuracy on held-out benchmarks with no per-graph tuning and no LLM.

  28. Turning Tabular Foundation Models into Graph Foundation Models

    cs.LG 2025-08 conditional novelty 6.0 of 10

    G2T-FM converts graph node tasks into tabular tasks and shows that tabular foundation models can match or beat well-tuned GNNs, especially after finetuning.

  29. From Nodes to Narratives: Explaining Graph Neural Networks with LLMs and Graph Context

    cs.LG 2025-08 unverdicted novelty 6.0 of 10

    GSPELL projects GNN embeddings into LLM space and builds hybrid prompts to produce faithful natural-language explanations and sparse subgraphs for GNN predictions on text-attributed graphs.

  30. OpenRTAG: A Comprehensive Benchmark for Robust Text-Attributed Graph Learning under Data Quality Degradation

    cs.AI 2026-07 conditional novelty 5.0 of 10

    OpenRTAG is a benchmark that organizes text-attributed-graph data-quality issues into a 3x3 taxonomy (text/structure/label by sparsity/noise/imbalance) and evaluates model robustness across nine datasets and three tasks.

  31. X-LogSMask: Expand Transformer for Graph-Structured Data

    cs.LG 2026-07 unverdicted novelty 5.0 of 10

    X-LogSMask injects per-head powers of the normalized adjacency matrix via a logarithmic transform into Transformer attention, achieving SOTA results on 13 of 20 graph benchmarks while remaining competitive in a one-la...

  32. Boundary Embedding Shaping with Adaptive Contrastive Learning for Graph Structural Disentanglement

    cs.LG 2026-06 unverdicted novelty 5.0 of 10

    BES is an adaptive contrastive learning plug-in for GNNs that shapes boundary embeddings to disentangle spurious structural correlations, yielding 3.3% average gains in node classification.

  33. Boundary Embedding Shaping with Adaptive Contrastive Learning for Graph Structural Disentanglement

    cs.LG 2026-06 conditional novelty 5.0 of 10

    Boundary-focused contrastive "gravity" loss on selected boundary nodes improves GNN node classification by about one point over an equal-architecture baseline, but the claimed proofs do not cover the implemented loss.

  34. ERAlign: Energy-based Representation Alignment of GNNs and LLMs on Text-attributed Graphs

    cs.LG 2026-06 unverdicted novelty 5.0 of 10

    ERAlign aligns GNN and LLM embeddings on text-attributed graphs via energy-based models and an Energy Discrepancy objective, reporting state-of-the-art results on eight datasets under varying supervision.

  35. Fast and Featureless Node Representation Learning with Partial Pairwise Supervision

    cs.LG 2026-05 unverdicted novelty 5.0 of 10

    Contrastive FUSE learns node embeddings from partial pairwise supervision and structural signals alone by optimizing a spectral contrastive objective with a lightweight modularity approximation, yielding competitive p...

  36. S2Aligner: Pair-Efficient and Transferable Pre-Training for Sparse Text-Attributed Graphs

    cs.LG 2026-05 unverdicted novelty 5.0 of 10

    S2Aligner decouples semantic and structural components in LLM-based graph-text alignment, adds structure-oriented reconstruction with consistency control, and uses sparsity-aware risk balancing to reduce cross-domain ...

  37. Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification

    cs.LG 2026-05 unverdicted novelty 5.0 of 10

    Transductive Sharpening adds an entropy-minimization term on unlabeled-node predictions to the training objective for graph node classification.

  38. GP2F: Cross-Domain Graph Prompting with Adaptive Fusion of Pre-trained Graph Neural Networks

    cs.LG 2026-02 unverdicted novelty 5.0 of 10

    GP2F is a dual-branch graph prompting framework that fuses frozen pre-trained knowledge with task-specific adaptation to reduce estimation error and outperform baselines in cross-domain few-shot node and graph classification.

  39. Toward General Digraph Contrastive Learning: A Dual Spatial Perspective

    cs.LG 2025-10 conditional novelty 5.0 of 10

    S2-DiGCL combines personalized magnetic Laplacian perturbations with BFS/DFS path sampling to improve contrastive learning on directed graphs.

  40. AdvSynGNN: Structure-Adaptive Graph Neural Nets via Adversarial Synthesis and Self-Corrective Propagation

    cs.LG 2026-02 unverdicted novelty 4.0 of 10

    AdvSynGNN uses multi-resolution structural synthesis, contrastive objectives, an adaptive transformer, and an adversarial propagation engine with residual label correction to improve node-level predictions on challeng...

  41. Intellectual Property in Graph-Based Machine Learning as a Service: Attacks and Defenses

    cs.CR 2025-08 conditional novelty 4.0 of 10

    A systematic review that organizes graph-ML IP protection into model-level and data-level attacks and defenses, and ships a benchmark library, PyGIP.

Pith tools