Pith. sign in

REVIEW 21 cited by

Graph Neural Networks: A Review of Methods and Applications

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 1812.08434 v6 pith:U7YTQEC2 submitted 2018-12-20 cs.LG cs.AIstat.ML

Jie Zhou , Ganqu Cui , Shengding Hu , Zhengyan Zhang , Cheng Yang , Zhiyuan Liu , Lifeng Wang , Changcheng Li
show 1 more author
Maosong Sun
This is my paper · ORCID
classification cs.LGcs.AIstat.ML
keywords graphlearninggraphsmodelsnetworkneuralapplicationsdata
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Lots of learning tasks require dealing with graph data which contains rich relation information among elements. Modeling physics systems, learning molecular fingerprints, predicting protein interface, and classifying diseases demand a model to learn from graph inputs. In other domains such as learning from non-structural data like texts and images, reasoning on extracted structures (like the dependency trees of sentences and the scene graphs of images) is an important research topic which also needs graph reasoning models. Graph neural networks (GNNs) are neural models that capture the dependence of graphs via message passing between the nodes of graphs. In recent years, variants of GNNs such as graph convolutional network (GCN), graph attention network (GAT), graph recurrent network (GRN) have demonstrated ground-breaking performances on many deep learning tasks. In this survey, we propose a general design pipeline for GNN models and discuss the variants of each component, systematically categorize the applications, and propose four open problems for future research.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 21 Pith papers

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

  1. EnGN: A High-Throughput and Energy-Efficient Accelerator for Large Graph Neural Networks

    cs.DC 2019-08 conditional novelty 7.0 of 10

    EnGN, a simulated edge-centric GNN accelerator with ring-edge-reduce dataflow and degree-aware caching, claims 2.97x speedup and 6.2x energy efficiency over the HyGCN accelerator.

  2. An Analysis of Architectural and Operational Dynamics of Phishkits in the Wild

    cs.CR 2026-08 conditional novelty 6.0 of 10

    Analysis of 1,300 phishkits (2020-2023) finds heavy code reuse, simple evasion tricks, and widespread Telegram bot exfiltration, making phishkit-based phishing highly predictable.

  3. Rethinking Query Optimization for Multi-Agent Systems [Vision]

    cs.DB 2025-12 conditional novelty 6.0 of 10

    Agentic data pipelines are built by hand today; this paper sets a research agenda for automatically optimizing their structure, model choices, and execution engines jointly as a new query-optimization problem.

  4. Hot-Ham: an accurate and efficient E(3)-equivariant machine-learning electronic structures calculation framework

    physics.comp-ph 2025-09 conditional novelty 6.0 of 10

    Hot-Ham combines Gaunt tensor products with a local-coordinate SO(2) convolution to predict DFT Hamiltonians accurately and efficiently across several material classes.

  5. DEF: Diffusion-augmented Ensemble Forecasting

    cs.LG 2025-06 conditional novelty 6.0 of 10

    A conditional diffusion model that generates perturbed initial states can turn any deterministic neural weather forecast model into an ensemble, with measured error reduction on a single ERA5 case study.

  6. Tensor-Based Binary Graph Encoding for Variational Quantum Classifiers

    quant-ph 2025-01 reject novelty 6.0 of 10

    A tensor-based binary encoding maps graph vertices and edges to Pauli-Z strings for variational quantum classifiers, and simulations on three datasets show accuracy gains over a PCA-based baseline, with several unaddr...

  7. 3D representation in 512-Byte:Variational tokenizer is the key for autoregressive 3D generation

    cs.CV 2024-12 conditional novelty 6.0 of 10

    VAT is a variational tokenizer that maps 3D shape features into coarse-to-fine tokens in Gaussian subspaces, enabling autoregressive 3D generation and up to 2000x mesh compression.

  8. Swift: A Multi-FPGA Framework for Scaling Up Accelerated Graph Analytics

    cs.AR 2024-11 conditional novelty 6.0 of 10

    Swift uses a decoupled, asynchronous Gather-Apply-Scatter pipeline to scale graph analytics across multiple FPGAs in one node, reporting up to 12x speedup over the ForeGraph framework and 2.6x better energy efficiency...

  9. Material characterization and precise finite element analysis of fiber reinforced thermoplastic composites for 4D printing

    cs.CG 2019-09 conditional novelty 6.0 of 10

    A calibrated finite-element workflow predicts the heated bending of PLA and carbon-fiber-PLA composite 4D-printed grid structures with a reported 95% confidence interval accuracy of (0.972, 0.985).

  10. Context-Aware Graph Attention Networks

    cs.LG 2019-09 conditional novelty 6.0 of 10

    CaGAT couples tensor-product-graph diffusion of edge attention with node feature aggregation, and it reports consistent but modest accuracy gains over GAT on four citation benchmarks.

  11. HiCoRe: Visual Hierarchical Context-Reasoning

    cs.CV 2019-09 conditional novelty 6.0 of 10

    HiCoRe predicts an image's global class by running graph convolutions over complete graphs of its bounding boxes, and claims large gains over CNN baselines without using object labels.

  12. AHINE: Adaptive Heterogeneous Information Network Embedding

    cs.SI 2019-08 conditional novelty 6.0 of 10

    AHINE learns node embeddings in heterogeneous information networks by composing relation-type-specific neural network transforms along paths, and reports accuracy gains over meta-path and homogeneous baselines.

  13. F2STNet: Fair and Federated Spectral-Temporal Modeling for Graph Forecasting

    cs.LG 2026-08 conditional novelty 5.0 of 10

    F2STNet combines truncated graph Fourier features, a diagonal state-space temporal layer, and fairness-aware federated aggregation to improve graph forecasting accuracy and client fairness.

  14. Physics-Informed EvolveGCN: Satellite Prediction for Multi Agent Systems

    cs.MA 2025-07 reject novelty 4.0 of 10

    A physics-informed EvolveGCN that adds a Clohessy-Wiltshire-based loss term to satellite swarm trajectory prediction shows only mixed, preliminary improvements over the same model without physics.

  15. A Novel Framework Using Deep Reinforcement Learning for Join Order Selection

    cs.DB 2024-12 reject novelty 4.0 of 10

    GTDD combines GNN, Tree-LSTM, and Dueling-DQN to select SQL join orders, reporting lower costs than RTOS and JOGGER on JOB and TPC-H, but the comparison is weakened by modifying baselines to use its new reward function.

  16. GmCN: Graph Mask Convolutional Network

    cs.CV 2019-09 conditional novelty 4.0 of 10

    GmCN learns a binary mask that selects which neighbors each node aggregates over, leading to modest but consistent accuracy improvements on semi-supervised graph classification benchmarks.

  17. DWnet: Deep-Wide Network for 3D Action Recognition

    cs.CV 2019-08 conditional novelty 4.0 of 10

    DWnet, a deep plus broad network for skeleton action recognition, reaches accuracy near HCN on SBU and NTU datasets while reducing test time per sample by about 100 times.

  18. MVAN: Multi-View Attention Networks for Fake News Detection on Social Media

    cs.CL 2025-06 reject novelty 3.0 of 10

    MVAN, a model combining BiGRU text attention with graph attention over retweet structures, reports accuracy gains of roughly 2.5 percent over prior state-of-the-art on Twitter15 and Twitter16.

  19. Learning Isometric Embeddings of Road Networks using Multidimensional Scaling

    cs.LG 2025-04 reject novelty 2.0 of 10

    The paper proposes combining multidimensional scaling with road-network graph embeddings as feature spaces for generalizable autonomous driving motion planning, but provides only a literature review and toy visualizat...

  20. RouteNet-Fermi: Network Modeling With GNN (Analysis And Re-implementation)

    cs.NI 2024-12 conditional novelty 2.0 of 10

    Replacing GRU cells in RouteNet-Fermi with LSTMs gives slightly lower delay MAPE on several test networks, but this is a routine extension with weak statistical support.

  21. Linking Points With Labels in 3D: A Review of Point Cloud Semantic Segmentation

    cs.CV 2019-08 accept novelty 1.0 of 10

    A structured review that organizes point cloud semantic segmentation methods, datasets, and open issues into a single reference.

Pith tools