Graphs of various types, such as plain networks, linked/semantic web/RDF data, attributed, dynamic, interaction graphs, and possible combinations of these, are increasingly used as versatile and practical models for data encountered in today’s data-intensive research and industries. In contrast to data tables, graphs allow capturing the information about entities (using attributes or properties), as well as the relational structure between entities.
The ability to discover knowledge from and make predictions about such network data has gained in importance quickly. However, both for the formalization of new problem types that match well with practical use cases, as well as the algorithmic, statistical, and information theoretic aspects of such problems require further scientific inquiry. The workshop also takes a particular interest in the very popular topic of representation learning (network embeddings), which as intermediate real-valued representation enables learning and mining algorithms devised for non-relational data to be applied to graphs. With rapid advances in this area in particular, trustworthy AI on graphs requires particular attention.
The aim of this workshop, to be held in conjunction with ECML-PKDD Conference, is to be a discussion forum for the most recent advances on these topics. We will encourage both theoretical and practical contributions to stimulate interactions between participants, by separating long mature contributions and short, open for discussion, ideas.
Topics of interests include
Representation learning
- Network embedding
- Graph compression
- Knowledge graph embedding
- Graph neural networks
- Entity resolution/deduplication
- Clustering
Trustworthy AI on Graphs
- Algorithmic biases
- Algorithms and metrics for fairness
- Explainable graph learning
- Privacy preserving graph learning
Pattern mining
- Local patterns: community detection, subgraph mining
- Graph summarization
- Subgroup discovery on graphs
Complex Network analysis
- Attributed networks
- Evolving graphs
- Probabilistic and uncertain Networks
Supervised learning
- Classification
- Graph Kernels
- Link prediction
- Anomaly detection
- Knowledge graph completion
Exploration
- Visualization
- Visual analytics
Modeling
- Random graph models
- Opinion formation
- Information propagation
Data management for graph analytics
- Data models and structures
- Index structures
Applications
- Social network analysis
- Biological networks and life science data
- Communication networks
- User-item interaction networks in the recommendation scenario
- Urban data, traffic networks
All types of approaches are welcome, e.g., graph neural networks, traditional ML, random walk methods, Bayesian inference, information theoretical approaches, and we encourage authors to consider the breadth of graph data types (attributed, dynamic graphs, etc.).
The workshop
The workshop will feature
- keynote speakers,
- a few contributed talks,
- a poster session, and
- small-group discussions on hot topics that are aimed to bring together academia and industry or end-users in application areas. It will be accompanied by a half-day tutorial dedicated to machine learning and analysis of large real-world graphs with scikit-network.