Special Sessions
Special sessions are very small and specialized events to be held during the conference as a set of oral and poster presentations that are highly specialized in some particular theme or consisting of the works of some particular international project. The goal of special sessions (minimum 4 papers; maximum 9) is to provide a focused discussion on innovative topics. All accepted papers will be published in a special section of the conference proceedings book, under an ISBN reference. The proceedings are abstracted/indexed in DBLP, Google Scholar, EI-Compendex, INSPEC, Japanese Science and Technology Agency (JST), Norwegian Register for Scientific Journals and Series, Mathematical Reviews, SCImago, Scopus and zbMATH. CCIS volumes are also submitted for the inclusion in ISI Proceedings.
Symposia proposals are accepted until:
March 18, 2026
If you wish to propose a new Special Session please kindly fill out and submit this
Expression of Interest form.
![]()
SYMPOSIA/SPECIAL SESSIONS LIST
KAN-ADIA 2026, Special Session on Kolmogorov-Arnold Networks (KANs): Advances in Design, Implementations and Applications
Chair(s): Samira Sadaoui and Ali Bayeh
Special Session on Kolmogorov-Arnold Networks (KANs): Advances in Design, Implementations and Applications -
KAN-ADIA
2026
Paper Submission:
May 22, 2026
Authors Notification:
June 8, 2026
Camera Ready and Registration:
June 17, 2026
Scope
Kolmogorov-Arnold Networks (KANs) decompose complex, multidimensional functions into structured compositions of univariate components. This approximation enables KANs to learn univariate edge functions during training, unlike traditional neural networks with fixed activation functions. The learnable edge functions allow KANs to adapt more effectively to complex data patterns. This adaptability increases KAN expressiveness and enables smaller KAN architectures to match or even outperform the performance of larger Multi-Layer Perceptron (MLPs). Since each edge function can be directly examined, KANs also improve interpretability. Although KANs demonstrate strong potential in terms of expressiveness, generalization, compactness, and interpretability, research on them is still ongoing.