Pith. sign in

REVIEW 15 cited by

A Survey on Graph Structure Learning: Progress and Opportunities

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 2103.03036 v2 pith:H4O72NSB submitted 2021-03-04 cs.LG cs.SI

Yanqiao Zhu , Weizhi Xu , Jinghao Zhang , Yuanqi Du , Jieyu Zhang , Qiang Liu , Carl Yang , Shu Wu This is my paper · ORCID
classification cs.LGcs.SI
keywords graphstructuregraphslearningmethodsprogressrecentrepresentations
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Graphs are widely used to describe real-world objects and their interactions. Graph Neural Networks (GNNs) as a de facto model for analyzing graphstructured data, are highly sensitive to the quality of the given graph structures. Therefore, noisy or incomplete graphs often lead to unsatisfactory representations and prevent us from fully understanding the mechanism underlying the system. In pursuit of an optimal graph structure for downstream tasks, recent studies have sparked an effort around the central theme of Graph Structure Learning (GSL), which aims to jointly learn an optimized graph structure and corresponding graph representations. In the presented survey, we broadly review recent progress in GSL methods. Specifically, we first formulate a general pipeline of GSL and review state-of-the-art methods classified by the way of modeling graph structures, followed by applications of GSL across domains. Finally, we point out some issues in current studies and discuss future directions.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 15 Pith papers

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

  1. AutoGrable: What Is a Good Graph for a Table?

    cs.LG 2026-08 conditional novelty 7.0 of 10

    AutoGrable selects table columns for graph construction using a training-free label-alignment score, and matches or beats task-aware constructors on real benchmarks.

  2. Federated Graph Learning with Graphless Clients

    cs.LG 2024-11 conditional novelty 7.0 of 10

    FedGLS trains federated graph models when some clients have only node features and no graph edges, by distilling structure knowledge into a feature encoder and generating graphs locally on graphless clients.

  3. Edge Sparsification via Temporal Forman-Ricci Curvature for Dynamic Graph Learning

    cs.LG 2026-08 conditional novelty 6.0 of 10

    TRicci removes about 80% of edges in temporal graphs while preserving 97.7% of full-graph ROC-AUC and cutting end-to-end runtime by 55.94% on graph-level prediction tasks.

  4. ReGraph: Learning to Generate Recipe Graphs from Food Images

    cs.AI 2026-08 conditional novelty 6.0 of 10

    A structured recipe-graph dataset and a supervised plus reinforcement fine-tuning framework for generating cooking-procedure graphs from food images, with a benchmark showing text quality does not imply procedural structure.

  5. Multi-Domain Graph Foundation Models: Robust Knowledge Transfer via Topology Alignment

    cs.SI 2025-02 conditional novelty 6.0 of 10

    MDGFM aligns graph topologies across domains with learnable tokens and structure refinement, improving few-shot transfer to unseen graphs.

  6. 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.

  7. GraphFLEx: Structure Learning Framework for Large Expanding Graphs

    cs.LG 2025-05 reject novelty 5.0 of 10

    GraphFLEx uses clustering, hashing-based coarsening, and local graph learning to incrementally infer structure in large expanding graphs, claiming faster runtime and near-original accuracy.

  8. Bi-level Mean Field: Dynamic Grouping for Large-Scale MARL

    cs.AI 2025-05 conditional novelty 5.0 of 10

    BMF uses VAE-based dynamic agent grouping plus within-group mean-field and cross-group attention to improve large-scale cooperative and competitive multi-agent reinforcement learning.

  9. Graph Structure Refinement with Energy-based Contrastive Learning

    cs.LG 2024-12 conditional novelty 5.0 of 10

    A new framework, ECL-GSR, uses energy-based contrastive learning to refine noisy graph structure and reports state-of-the-art node classification accuracy on eight benchmarks.

  10. DG-Mamba: Robust and Efficient Dynamic Graph Structure Learning with Selective State Space Models

    cs.LG 2024-12 conditional novelty 5.0 of 10

    DG-Mamba combines Mamba state space models, kernelized attention, and a Principle of Relevant Information regularizer to learn robust dynamic graph structures in linear time.

  11. Temporal Attention Evolutional Graph Convolutional Network for Multivariate Time Series Forecasting

    cs.LG 2025-05 conditional novelty 4.0 of 10

    TAEGCN combines masked multi-head attention and a GRU-driven evolving graph to model temporal and spatial dependencies in multivariate traffic forecasting, reporting lower errors than baselines on METR-LA and PEMS-BAY.

  12. Graph-Augmented Large Language Model Agents: Current Progress and Future Prospects

    cs.AI 2025-07 conditional novelty 3.0 of 10

    A survey that categorizes Graph-augmented LLM Agent research into planning, memory, tool management, and multi-agent design, and outlines open directions.

  13. A Comprehensive Survey on Spectral Clustering with Graph Structure Learning

    cs.LG 2025-01 unverdicted novelty 3.0 of 10

    A survey organizes spectral clustering methods around graph structure learning, covering fixed and adaptive pairwise, anchor, and hypergraph graphs in single- and multi-view settings.

  14. Finding the Cores of Higher Graphs Using Geometric and Topological Means: A Survey

    math.HO 2025-06 accept novelty 2.0 of 10

    A structured review of geometric and topological methods for extracting small core representations from graphs, hypergraphs, and simplicial complexes.

  15. Deep Learning for Ophthalmology: The State-of-the-Art and Future Trends

    eess.IV 2025-01 conditional novelty 2.0 of 10

    A survey of deep learning applications in ophthalmology covering diabetic retinopathy, glaucoma, AMD, and retinal vessel segmentation, with datasets and future directions.

Pith tools