Home Schedule Speakers Organizers Accepted Papers

Overview and Objective

Graph, as a unified data structure representing relationships among entities, exists universally across different domains, including computer science, social science, physics, chemistry, biology, infrastructure, finance, psychology, etc. Many real-world applications could be formulated as graph-based tasks. For example, social anomaly detection, drug property prediction, product recommendation can be regarded as node/graph classification and link prediction tasks, academic paper question-answering requires retrieving documents from citation networks, agent collaboration and communication can be regarded as a graph structure optimization task, designing molecules and infrastructure networks can be deemed as a graph generation task, optimizing sensor localization can be formulated as an influence-maximization-based decision-making task.

Through years of research, graph machine learning has gradually formed a well-established ecosystem capable of automating these tasks and driving real-world applications. With the increasing maturity of GML, the recent emergence of large foundational models, such as large language models and multi-modal systems, has propelled machine learning into a new AGI era and revolutionized the research landscape of many fields. However, the well-established GML is still predominately anchored in pre-AGI paradigms, creating a significant gap in understanding how it should evolve to fully leverage the opportunities, address the challenges, and comprehensively embrace this transformative AGI era. This motivates us to host this workshop to gather academic and industrial researchers/practitioners to present and share the development of GML in the AGI paradigm and envision how GML communities could embrace this new AGI era.

Topics

  • Agentic Learning
  • Multi-Agentic Collaboration
  • Graph-enhanced Agentic Reasoning and Planning
  • Graph-based Memory Systems
  • Agentic Social Network Analysis
  • Multi-Modal Graph Learning
  • Text-rich Graph Learning
  • Image-rich Graph Learning
  • Graph and Other Modality Learning
  • Neural-Symbolic Harmonization
  • Symbolic-enhanced Neural Learning
  • Neural-enhanced Symbolic Learning
  • Knowledge Representation
  • Learning and Inference
  • Logic and Reasoning
  • Graph Retrieval-augmented Generation (GraphRAG)
  • Graph-enhanced Retrieval
  • Graph-enhanced Generation
  • Graph Knowledge Base Construction and Management
  • Query Topology Analysis
  • Agentic Graph Retrieval
  • Graph Generative Models
  • Continuous Graph Diffusion
  • Discrete Graph Diffusion
  • LLM for Graph Generation
  • Complex Graph Generation: Multi-attributed Graph, Dynamic Graph Generation, etc.
  • Expressiveness and Generalization of Graph Models
  • Expressiveness of Graph Machine Learning Models
  • Complex Topology Modeling
  • Graph Foundational Models
  • Foundational Graph Model Design
  • Graph Transferability Analysis
  • LLMs for Graph Learning
  • Graph Combinatorial Optimization
  • Scalable Graph Machine Learning
  • Data-centric Graph Machine Learning
  • Distribution Shift
  • Imbalance
  • Limited Supervision
  • Trustworthy Graph Machine Learning
  • Reliability
  • Robustness
  • Resilience
  • Privacy
  • Explainability
  • Attack and Defense
  • Applications
  • Social Network Analysis
  • Recommender System
  • Neural Biology
  • Biochemistry
  • Cybersecurity
  • Infrastructure Networks
  • Spatial-Temporal Learning
  • Document Mining
  • Psychology
  • Computer System
  • Hardware Design

    • Submission Details

    We welcome submissions of papers ranging from 4 to 8 pages as main content, with up to 2 additional pages containing references and an optional appendix. All submissions must be in PDF format and formatted according to the new ACM format published in ACM guidelines (e.g., using the ACM LaTeX template on Overleaf here) and selecting the “sigconf” sample. Following the WWW’24 conference submission policy, reviews are double-blind, and author names and affiliations should NOT be listed. Submitted works will be assessed based on their novelty, technical quality, potential impact, and clarity of writing (and should be in English). For papers that primarily rely on empirical evaluations, the experimental settings and results should be clearly presented and repeatable. We encourage authors to make data and code available publicly when possible.
    Accepted papers will be posted on this workshop website. By default, accepted papers will not appear in the KDD’25 proceedings and are thus non-archival. This allows authors to submit works that are concurrently under review elsewhere or published.
    The best paper (according to the reviewers’ ratings and organizing committee) will be announced at the end of the workshop.
    At least one of the authors of the accepted workshop papers must register for the workshop and be present on the day of the workshop.
    For questions regarding submissions, please contact us at: yuwang@uoregon.edu

    Important Dates

    The important dates of the workshop should not be later than:

  • Workshop paper submission: May 8th, 2025
  • Workshop paper notification: June 8th,2025
  • Workshop paper camera-ready: June 15th, 2025
  • Workshop date: August 6th, 2025