The primary objective of the NEGEL workshop at TheWebConf 2025 is to create a collaborative platform for researchers, industry professionals, and academics from diverse fields. These include non-Euclidean representation learning, geometric deep learning, and large foundation models, as well as web-related applications such as recommender systems, social network analysis, web knowledge graphs, search systems, information retrieval, and multi-modal web content understanding. The workshop aims to foster knowledge sharing, idea exchange, and discussions on the latest advancements and challenges in these domains.

We encourage in-person participation, but remote presentations will be available for authors who cannot travel to Sydney.

Topics and Scope

(1) Architectures, Algorithms, and Large Foundation Models (including LLMs, ViTs, and multi-modal models)

  • Developing novel architectures and algorithms by integrating foundation models with non-Euclidean geometries, mixed-curvature spaces, and geometric principles.
  • Adapting LLMs, ViTs, and multi-modal models to operate within non-Euclidean or geometric settings.
  • Creating new foundation models specifically tailored for non-Euclidean and geometric spaces.
  • Combining non-Euclidean architectures, such as hyperbolic, spherical, mixed-curvature models, and graph neural networks, with foundation models.
  • Applications of these models to web-related tasks such as search, recommendation, content understanding, and topology-aware data processing.

(2) Adapting and Enhancing Existing Large Language/Foundation Models

  • Fine-tuning, continual learning, and adaptation of existing foundation models for specific tasks in non-Euclidean and geometric contexts.
  • Leveraging advanced frameworks like GraphRAG (Graph Retrieval-Augmented Generation) to improve knowledge-driven applications.
  • Enabling agent-like capabilities for interactive, adaptive problem-solving and real-time decision-making in complex geometric and non-Euclidean spaces.
  • Integration of graph-based reasoning and domain-specific geometric representations into existing foundation models.

(3) Theoretical Foundations

  • Investigating generalization error, trainability, representation precision, and curvature-dimension tradeoff in non-Euclidean and geometric models.
  • Contributions analyzing properties such as curvature, geodesics, isometries, and their effects on the performance of foundation models.
  • Studies on the expressive power of non-Euclidean and geometric representation.

  • (4) Geometric Deep Learning

  • Advances in geometric learning frameworks, including graph neural networks, message-passing networks, and equivariant models.
  • Applications of geometric deep learning to social networks, graphs, multi-modal data, and structured representations.
  • Exploration of geometric biases in learning algorithms to improve scalability, efficiency, and interpretability.
  • Case studies demonstrating the use of geometric deep learning in domains such as content understanding, recommendations, and real-time analytics.

(5) Web Applications and Case Studies

  • Applications of non-Euclidean and geometric methods in social network analysis, web knowledge graphs, search systems, recommender systems, and multi-modal content understanding.
  • Real-world demonstrations highlighting improved performance and scalability in web-specific tasks through geometric and non-Euclidean representations.

(6) Trustworthiness and Robustness

  • Addressing fairness, interpretability, privacy, and adversarial robustness in geometric and non-Euclidean learning systems.
  • Specific challenges and solutions for trustworthiness in user-facing web applications and sensitive data processing.

(7) Benchmarks and Evaluation

  • Development of NEGEL-related datasets, evaluation protocols, and benchmarking tools for geometric and non-Euclidean models.
  • Metrics for assessing real-world performance, scalability, and efficiency.

Submission Guidelines

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) and selecting the “sigconf” sample.

Manuscripts will be reviewed by our program committee through a single-blind review process**. Accepted submissions will be presented either as oral talks or posters during the workshop.

Submission Policy

  • Authors of unpublished papers accepted to the workshop may choose to have their work published in the Companion Proceedings of TheWebConf 2025, provided they meet the camera-ready submission deadline.
  • Papers not included in the Companion Proceedings of TheWebConf 2025 can be freely submitted to other venues in the future.
  • Previously published or under-review work are also welcome for submission to the workshop but will not be included in the Companion Proceedings of TheWebConf 2025. Authors should use the standard ACM template and clearly indicate the prior publication status of their paper.
  • All accepted papers will be archived on the workshop’s website.

This policy encourages open discussions while respecting the integrity of prior and future publications.

Accepted papers will be presented as posters, with selected papers highlighted for oral presentations and outstanding paper awards.

Paper Format

All submissions must be in English and must adhere to the ACM template and format (also available in Overleaf), with the following options:

\setcopyright{none}

CCS class and keywords sections are optional.

Submission Site

Submission site:https://openreview.net/group?id=ACM.org/TheWebConf/2025/Workshop/NEGEL

Important Dates

  • 2025-02-01: Paper submission deadline (Extended)   
  • 2025-02-03: Author notification (Extended)
  • 2025-02-07: Camera-ready submission
  • 2025-04-28: Workshop at TheWebConf 2025 (Whole-day session)
  • Submission site: https://openreview.net/group?id=ACM.org/TheWebConf/2025/Workshop/NEGEL
  • Venue: International Convention & Exhibition Centre (ICC), Sydney, Australia
  • Timezone: Anywhere On Earth (UTC-12)