Description

Graphs have gained a lot of attention in the pattern recognition community thanks to their ability to encode both topological and semantic information. Despite their invaluable descriptive power, their arbitrarily complex structured nature poses serious challenges when they are involved in learning systems. The complexity of graph data carries significant challenges for existing algorithms. Some (but not all) of challenging concerns are: a non-unique representation of data, heterogeneous attributes (symbolic, numeric, etc.), and so on. Furthermore, in the machine learning context, even other important issues are addressed. For example, as graphs can be irregular, a graph may have a variable size of unordered nodes, and the nodes may have a different number of neighbors, resulting in some important operations (e.g., convolutions) that are easy to compute in a vector domain, but difficult to apply to the graph domain. In recent years, due to their widespread applications, graph-based learning algorithms have gained much research interest. Encouraged by the success of CNNs, a wide variety of methods have redefined the notion of convolution for graphs and provided, in particular, a suitable representation for ubiquitous spatio-temporal data. These new approaches have in general enabled effective training and achieved in many cases better performances than competitors, though at the detriment of computational costs. Typical examples of applications dealing with graph-based representation are: scene graph generation, point clouds classification, and action recognition in computer vision; text classification, inter-relations of documents or words to infer document labels in natural language processing; forecasting traffic speed, volume or the density of roads in traffic networks, whereas in chemistry researchers apply graph-based algorithms to study the graph structure of molecules/compounds. This track as a whole intends to focus on all aspects of graph-based representations and models for learning and recognition tasks.

Topics

Track topics include but are not limited to:

• Graph Neural Networks: theory and applications


• Deep learning on graphs


• Graph or knowledge representational learning


• Graphs in pattern recognition


• Graph databases and linked data in AI


• Benchmarks for GNN


• Dynamic, spatial and temporal graphs


• Graph methods in computer vision


• Human behavior and scene understanding


• Social networks analysis


• Data fusion methods in GNN


• Efficient and parallel computation for graph learning algorithms


• Reasoning over knowledge-graphs


• Interactivity, explainability and trust in graph-based learning


• Probabilistic graphical models


• Biomedical data analytics on graphs

Call for paper

• Download PDF file
• Download txt file

Regular Paper

Each paper will be double-blindly reviewed by at least three reviewers; this is an ACM requirement as SAC is a “Refereed Conference”. Please adhere to this requirement when you prepare for your paper. Double-blindly means that the author of a paper does not know the reviewers of his/her paper and reviewers do not know the authors of the papers they reviewed.
Poster Sessions: Papers that received high reviews (that is acceptable by reviewer standards) but were not accepted due to space limitation can be invited for the poster session.
Original manuscripts should be submitted in electronic format through the START system used by SAC 2023 conference

• Author kit is HERE
• Submission page is HERE

Student Research Competition (SRC)

Students are invited to submit research abstracts (maximum of 4 pages in ACM camera-ready format) following the instructions published at the SAC 2023 website. Submission of the same abstract to multiple tracks is not allowed. All research abstract submissions will be reviewed by researchers and practitioners with expertise in the track focus area to which they are submitted.
Authors of selected abstracts (up to 18 students) will have the opportunity to give poster and oral presentations of their work and compete for three top-winning places. The SRC committee will evaluate and select First, Second, and Third place winners. The winners will receive medals and cash awards. Winners will be announced during the conference banquet. Invited students receive SRC travel support (US$500) and are eligible to apply to the SIGAPP Student Travel Award Program (STAP) for additional travel support.

• Author kit is HERE
• Submission page is HERE

SAC No-Show Policy

Paper registration is required, allowing the inclusion of the papers and posters in the conference proceedings. An author or a proxy attending SAC MUST present the paper. This is a requirement for all accepted papers, posters, and invited SRC submissions to be included in the ACM digital library. No-show of scheduled papers, posters, and student research abstracts will result in excluding them from the ACM digital library.

Authors who cannot make on-site presentations due to travel restrictions by governments or institutions, or those for whom travel is inadvisable due to medical reasons may request to present their materials online

Proceedings

Accepted Papers and Posters and Session Preparation:

• The length of the paper is 8 page (included in the registration) + 2 pages (at extra charge) = 10 pages maximum.
• The length of the poster is 3 pages (included in the registration) + 1 page (at extra charge) = 4 pages maximum.
• The length of the SRC abstract is 4 pages maximum.

Accepted papers will be published in the annual conference proceedings and will be included in the ACM digital library. Paper registration is required, allowing the inclusion of the paper, poster, or SRC abstract in the conference proceedings. An author or a proxy attending SAC MUST present the paper. This is a requirement for including the work in the ACM/IEEE digital library. No-show of registered papers, posters, and SRC abstracts will result in excluding them from the ACM/IEEE digital library.