Special Sessions

Special Session on “Machine Learning and Causal Inference for Economic Applications”

Special Session Organizers:

Falco J. Bargagli Stoffi, Harvard University, USA. fbargaglistoffi@hsph.harvard.edu

Kristof De Witte, KU Leuven, Belgium. kristof.dewitte@kuleuven.be

Giorgio Stefano Gnecco, IMT School for Advanced Studies, Lucca, Italy. giorgio.gnecco@imtlucca.it

Marco Gori, University of Siena, Italy. marco.gori@unisi.it

Massimo Riccaboni, IMT School for Advanced Studies, Lucca, Italy.  massimo.riccaboni@imtlucca.it

Paper Submission Deadline: Tuesday May 3, 2022 (AoE)

https://easychair.org/my/conference?conf=lod2022

In recent years, machine learning has found application in almost every research field, including economics. At the same time, scholars have started developing methods at the interplay between machine learning and causal inference. The influence of these methodologies is witnessed by the awarding of the 2021 Nobel Memorial Prize in Economics to Guido W. Imbens, who recognized in his works the instrumentality of causal inference and machine learning for real-world evidence. Applications can be the source of further developments, with the aim of finding the most suitable machine learning technique, and/or improving an existing methodology, by taking into account specific issues of that application. For instance, in the case of causal inference, it is not possible to observe all potential outcomes associated with each single unit (i.e., in the case of a binary treatment the ones under treatment and under control), which makes the straightforward application of supervised learning methods problematic. With such premises, this special session calls for contributions which provide theoretical studies, algorithmic developments, and applications of machine learning for causal inference, with special emphasis to their policy implications in economics. Topics of interest include, but are not limited to, the following:

● Causal trees and causal forests: methods and applications
● Computationally efficient machine learning algorithms for causal inference
● Economic applications of causal machine learning
● Gaussian processes regression for counterfactual generation
● Machine learning for the discovery and estimation of heterogeneous causal effects
● Machine learning methods for causal panel data models
● Matrix completion for causal inference
● Multi-armed bandits for online experiments
● Trade-off between precision and sample size in causal inference
● Variables selection for estimating treatment effects
● Policy optimization via causal machine learning
● Interpretable machine learning for causal inference
● Algorithmic fairness in causal machine learning

 

Special session on “AI for Network/Cloud Management”

Special Session Organizer: Cloud Core Network Team, Huawei Ireland Research
Centre, Dublin, Ireland

Contact: stefano.mauceri1@huawei.com

Paper Submission Deadline: Tuesday May 3, 2022 (AoE)

https://easychair.org/my/conference?conf=lod2022

In the telecom industry, most network services have been virtualized and deployed on top of the cloud infrastructure. As a result, efficient management of both the network and underlying cloud technology has become crucial.
It is expected that AI will be able to automate a large set of vastly different tasks required for deploying, managing, and optimizing computer networks. With this prospect, the networking community will arguably face great challenges in the years ahead. This special session is a space where researchers from both industry and academia can gather to present and debate problems, best practices, and latest cutting-edge technologies in this critical field. Topics of interest include but are not limited to:

● Operational Analytics and Intelligence
● Event, Log and Big Data Analytics
● Network Monitoring
● Predictive Maintenance
● Fault Localization and Recovery
● Digital Twins
● Autonomous and Autonomic Networks
● Fog/Edge Computing
● Cognitive and Software Defined Networks
● Network Function Virtualization
● Large-scale Network Simulation
● Security, Fault, Performance, and Resource Management
● QoS and QoE Assurance and Management
● Use Cases of Federated Learning, Graph Neural Networks, Knowledge Graphs, etc.

 

Special Session on “Recent Advances in Deep Learning for Graphs”

Special Session Organizers:

Ming Li, Zhejiang Normal University, China. mingli@zjnu.edu.cn

Alessio Micheli, University of Pisa, Italy.  micheli@di.unipi.it

Giorgio Stefano Gnecco, IMT School for Advanced Studies, AXES Research Unit, Lucca, Italy. giorgio.gnecco@imtlucca.it

Marcello Sanguineti, University of Genoa, Italy.  marcello.sanguineti@unige.it

Federico Errica, NEC Laboratories Europe, Germany and U. of Pisa, Italy. federico.errica@neclab.eu

Franco Scarselli, University of Siena, Italy. franco.scarselli@unisi.it

Paper Submission Deadline: Tuesday May 3, 2022 (AoE)

https://easychair.org/my/conference?conf=lod2022

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. To address them, different styles of deep neural networks for graphs
(DNNG) have been proposed, spanning from the recursive approach of Graph Neural Networks to the multi-layered Convolutional Neural Networks for Graphs. With the term Deep Graph Networks (DGN), we can denote a broader class of models which includes neural, Bayesian, and generative deep learning models for graphs. In their various incarnations, DGNs have become a topic of immense interest at both theoretical and practical levels, thanks to the remarkable richness of the learned graph representations when applied to the tasks of node/graph classification, graph generation, and link prediction. DGNs and
related methods can be used in countless applications, ranging from molecule properties (e.g., energy or biological activities) prediction and drug repurposing to recommender systems in e-commerce and intelligent transportation. The ever increasing stream of publications about the topic of deep learning for graphs is indicative of the research questions that arise at both academic and industrial levels, where
there is a considerable demand for more advanced technologies and algorithms, theoretical foundations, as well as tools and platforms for real-world applications that can overcome well-known issues in the field. The goal is, therefore, to develop a broad class of new models and algorithms of different nature, be it spectral, spatial, recursive, or a combination of these, which can thrive in highly competitive and practical scenarios such as large-scale, dynamic, and ambiguous graphs with missing node features or edges. Proper mathematical formulations and sound theories are also needed to characterize the power and limitations of DGNs. Put simply, this special session focuses on theoretical studies, model designs, algorithmic developments, and advanced applications of the field of deep learning for graphs.

Topics of Interests
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 Neural Networks for Graphs and Deep Graph Networks novel approaches
• Novel DNNG Architectures
• Deep Learning for Graphs
• Graph Representation Learning
• Fast and/or Distributed Learning Algorithms for DNNG/DGNs
• Spectral-based and Spatial-based Methods
• Novel Approaches to Graph Convolution, Recursion on Graphs
• Novel Graph Pooling, Graph Attention, Message Passing Mechanisms on Graphs
• Algorithms for Pre-Trained DNNG/DGNs, Graph Transformer Networks
• Spectral Graph Theory, Graph Wavelets
• Expressive, Generalization and Representational Power of DNNG/DGNs
• Universality of Invariant or Equivariant DNNG/DGNs
• Learning Theory on DNNG/DGNs
• Probabilistic and Generative Models of Graphs
• Combination of Neural Networks for Graphs and Gaussian Processes
• Heterogeneous DNNG/DGNs, Hyper-DNNGs, Multi-View DNNGs
• 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 DNNG/DGNs 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.

 

Special session on “Machine Learning for Fintech”

Special Session Organizer: Gianfranco Lombardo, Ph.D., University of Parma, Italy

Contact: gianfranco.lombardo@unipr.it

Paper Submission Deadline: Tuesday May 3, 2022 (AoE)

https://easychair.org/my/conference?conf=lod2022

Fintech applications seek to improve and automate the delivery and use of financial services at several levels for different stakeholders. In particular it can help private investors, hedge funds, companies and business owners to better manage their financial operations. In this field, Machine Learning techniques play a key role in providing solutions for forecasts, document analysis, portfolio optimization and selection, trading strategies and others. Many open problems are becoming relevant in this domain, especially the ones related to data availability, continual learning approaches and Natural Language Processing techniques able to deep analyze and extract knowledge from financial documents and reports. Topics of interest include, but are not limited to:

●  Continual Learning in the financial domain
●  Machine Learning-based trading strategies
●  Natural Language Processing for financial analysis
●  Machine Learning for Asset pricing
●  Graph Machine Learning for FinTech applications
●  Knowledge extraction from documents
●  Reinforcement learning approaches for FinTech
●  Financial networks analysis
●  Representation learning in the financial domain
●  Bankruptcy prediction
●  Machine learning for Portfolio selection

 

Tracks:

I) Track on “AI for Sustainability

Paper Submission Deadline: Tuesday May 3, 2022 (AoE)

https://easychair.org/my/conference?conf=lod2022

 

II) Track on “AI to help to fight Climate Change

World Economic Forum report, Harnessing Artificial Intelligence for the Earth.

Paper Submission Deadline: Tuesday May 3, 2022 (AoE)

https://easychair.org/my/conference?conf=lod2022

 

III) The 7 Tracks on “Machine Learning”

  • Multi-Task Learning
  • Reinforcement Learning
  • Deep Learning
  • Generative Adversarial Networks
  • Deep Neuroevolution
  • Networks with Memory
  • Learning from Less Data and Building Smaller Models

Paper Submission Deadline: Tuesday May 3, 2022 (AoE)

https://easychair.org/my/conference?conf=lod2022

 

IV) The 7 Tracks on “Data Science and Artificial Intelligence”

  • Simulation Environments to understand how AI Systems Learn
  • Chatbots and Conversational Agents
  • Data Science at Scale & Data in the Cloud
  • Urban Informatics & Data-Driven Modelling of Complex Systems
  • Data-centric Engineering
  • Data Security, Traceability of Information & GDPR
  • Economic Data Science

Paper Submission Deadline: Tuesday May 3, 2022 (AoE)

https://easychair.org/my/conference?conf=lod2022

 

V) Track on “Multi-Objective Optimization”

  • Comparative studies of various many-objective optimization techniques
  • Designing and constructing many-objective benchmark test problems
  • Designing quality/performance metrics for many-objective solutions/algorithms
  • Development of meta-heuristic algorithms for many-objective optimization problems
  • Evolutionary many-objective optimization methods in search-based software engineering
  • Evolutionary many-objective optimization methods applied to real-world problems
  • Exact methods from mathematical programming for many-objective optimization problems
  • Many-objective optimization in bi-level optimization problems
  • Many-objective optimization in combinatorial/discrete optimization problems
  • Many-objective optimization in computational expensive optimization problems
  • Many-objective optimization in constrained optimization problems
  • Many-objective optimization in dynamic environments
  • Many-objective optimization in large-scale optimization problems
  • Objective reduction techniques
  • Preference articulation in many-objective optimization
  • Preference-based search in many-objective optimization
  • Study of parameter sensitivity in many-objective optimization
  • Theoretical analysis and developments in many-objective optimization
  • Visualization for decision-making in many-objective optimization
  • Visualization for many-objective solution sets
  • Visualization for the search process of meta-heuristic algorithms
  • Multi-objective Optimization: new algorithms and concrete applications
  • Industrial problems, transportation and logistics problems
  • contributions to theoretical aspects of Multi-Objective Optimization (MOO) and Multi-Criteria Decision Aiding (MCDA)
  • descriptions of actual application cases
  • software contributions to MOO or MCDA
  • inter-disciplinary research, presenting the contributions of MOO and/or MCDA to other scientific disciplines, or integrating other disciplines into MOO or/and MCDA
  • decision aiding and multi-objective optimization for sustainability

Paper Submission Deadline: Tuesday May 3, 2022 (AoE)

https://easychair.org/my/conference?conf=lod2022