Connectionists: [CfP - Extended Deadline] Recent Advances in Deep Learning for Graphs - LOD22

[Federico Errica]

Call for Papers: "Recent Advances in Deep Learning for Graphs"
(Extended deadline)

Special Session of the 8th International Conference on machine
Learning, Optimization & Data science – LOD 2022
19 - 22nd September 2022, Certosa di Pontignano (Siena) Tuscany, Italy
Conference Page: https://lod2022.icas.cc/

Updated Important Dates
Papers submission (extended) deadline: May 3, 2022 (AoE).

Papers Submission System: Easy Chair
(https://easychair.org/conferences/?conf=lod2022)

How to submit: select the track "LOD - Special Session on Recent
Advances in Deep Learning for Graphs".


Description

The field of deep learning for graphs studies how to extend deep
learning techniques to data that are represented as a graph. A graph
is a data structure able to capture intricate forms of interrelations
between a set of possibly high-dimensional entities, and as such its
use is frequent in domains like biology, physics, computer graphics,
chemistry, and social networks, to name a few. This poses two
compelling challenges: on the one hand, one wants to design methods
that allow us to better study and comprehend the complex available
data; on the other hand, we need an efficient and effective way to
capture and encode the geometric patterns of the graphs.


Topics
This special session aims to provide a forum for both the academic and
industrial communities to report recent results related to (advanced)
deep graph networks from the perspectives of theory, models,
algorithms and applications. Topics appropriate for this special issue
include (but are not necessarily limited to):

- Deep Graph Networks Novel Approaches
- Novel Deep Neural Networks for Graphs Architectures
- Graph Representation Learning
- Fast and/or Distributed Learning Algorithms for Deep Graph Networks
- Spectral-based and Spatial-based Methods
- Novel Approaches to Graph Convolution, Recursion on Graphs
- Dynamical and Temporal Deep Graph Networks
- Novel Graph Pooling, Graph Attention, Message Passing Mechanisms on Graphs
- Algorithms for Pre-Trained Deep Graph Networks, Graph Transformer Networks
- Spectral Graph Theory, Graph Wavelets
- Expressive, Generalization and Representational Power of Deep Graph Networks
- Universality of Invariant or Equivariant Deep Graph Networks
- Learning Theory on Deep Graph Networks
- Probabilistic and Generative Models of Graphs
- Combination of Neural Networks for Graphs and Gaussian Processes
- Heterogeneous Deep Graph Networks, Hyper-Deep Graph Networks ,
Multi-View Deep Graph Networks
- Novel Learning Frameworks for Graph Classification, Node
Classification, Link Prediction
- Adversarial Attacks and Defenses on Graphs
- Trustworthy Approaches for Deep Learning on Graphs
- Applications based on Novel Deep Graph Networks to Physics,
Mathematics, - Chemistry, Biology, Computer Vision, Nature Language
Processing, Social Networks, Traffic Networks, Communication Networks,
Internet of Things, Recommender Systems, Urban Computing, Drug Design,
and their potential cross-modality, etc.

Important Dates (from LOD site, updated)

Papers submission deadline: May 3, 2022 (AoE).
Reviews Released to Authors: by June 3, 2022
Rebuttal Due: by Saturday June 10, 2022
Decision Notification to Authors: by Friday June 20, 2022
Camera Ready Submission Deadline: by Monday July 1, 2022

Organizers
- Ming Li, Zhejiang Normal University, China
- Alessio Micheli, University of Pisa, Italy
- Giorgio Stefano Gnecco, IMT School for Advanced Studies, Italy
- Marcello Sanguineti, University of Genoa, Italy
- Federico Errica, NEC Laboratories Europe, Germany
- Franco Scarselli, University of Siena, Italy