#AAAI2022 workshop round-up 3: design and manufacturing, and learning and reasoning

22 April 2022

share this:
AAAI22 banner

As part of the 36th AAAI Conference on Artificial Intelligence (AAAI2022), 39 different workshops were held, covering a wide range of different AI topics. We hear from the organisers of the workshops on AI-Based Design and Manufacturing, and Graphs and more Complex structures for Learning and Reasoning, who provide a summary of their events.

AI-Based Design and Manufacturing (ADAM)
Organisers: Aarti Singh (Carnegie Mellon University), Baskar Ganapathysubramanian (ISU), Chinmay Hegde (New York University, Mark Fuge (University of Maryland), Olga Wodo (University of Buffalo), Payel Das (IBM), Soumalya Sarkar (Raytheon)

The first AI for Design and Manufacturing (ADAM) Workshop, conducted virtually as part of AAAI-22, was organized in order to bring together world experts in core AI, scientific computing, geometric modeling, design, and manufacturing. The primary objectives were to outline the major research challenges in this rapidly growing sub-field of AI; cross-pollinate collaborations between AI researchers and domain experts in engineering design and manufacturing; and sketch open problems of common interest.

This one-day workshop consisted of two plenary talks, four keynote talks, and twenty-four lightning talks by authors of accepted papers. All papers accepted to the workshop were peer-reviewed by a technical program committee, and paper authors were invited to a two-hour (virtual) poster session for in-depth discussions.

The morning plenary talk was delivered by Professor Nathan Kutz (University of Washington), titled “The Future of Governing Equations”. Professor Kutz provided an enlightening overview of the emerging field of scientific machine learning and how data-driven strategies are increasingly being used to uncover the dynamics of complex multiscale systems. He also provided several recipes for systematic design and analysis of data-driven models for physical processes. The afternoon plenary talk was delivered by Professor Elizabeth Holm (Carnegie Mellon University), titled “Computer Vision in Material Science”. Professor Holm showcased a wide variety of applications in materials characterization (particularly at the microstructure scale) that can effectively leverage modern computer vision techniques. She made the case that AI advances such as transfer learning, data re-use, and physics-based modeling could likely be key in furthering progress in this domain.

The workshop concluded with an exciting panel discussion with speakers from academia, government, and industry, during which several questions were debated: the role of high-quality datasets in design applications, how best to incorporate physical constraints and resource budgets within AI models, the challenges in bridging gaps between different fields, and grand challenges over the next decade.

Graphs and more Complex structures for Learning and Reasoning (GCLR)
Organisers: Balaraman Ravindran (IIT Madras), Kristian Kersting (TU Darmstadt), Sriraam Natarajan (Univ. of Texas Dallas), Ginestra Bianconi (Queen Mary University of London), Philip S. Chodrow (UCLA), Tarun Kumar (IIT Madras), Deepak Maurya (Purdue University), Shreya Goyal (IIT Madras).

The study of complex graphs is a highly interdisciplinary field that aims to study complex systems by using mathematical models, physical laws, inference and learning algorithms, etc. Complex systems are often characterized by several components that interact in multiple ways with each other. Such systems are better modeled by complex graph structures such as edge and vertex labelled graphs (e.g., knowledge graphs), attributed graphs, multilayer graphs, hypergraphs, etc. In this 2nd GCLR workshop, we focused on various complex structures along with inference and learning algorithms for these structures. The current research in this area is concerned with extending existing ML algorithms as well as network science measures to these complex structures. This workshop brought together researchers from these diverse but related fields together to embark on interesting discussions on new challenging applications that require complex system modeling and discovering ingenious reasoning methods. There were several distinguished invited speakers with their research interests spanning the theoretical and experimental aspects of complex networks. The three key events of 2nd GCLR workshop were six invited talks, a poster session of accepted papers, and a panel discussion.

Invited Talks

Professor Bruno Ribeiro from Purdue University delivered a talk on the relationships between higher-order structures, such as hypergraphs and graph representation learning. Professor Jamie Haddock from UCLA continued the discussion on hypergraphs in her talk that was focused on community detection in hypergraphs by using a spectral method that utilizes information from the eigenvectors of the nonbacktracking or Hashimoto matrix.

The workshop held four exciting talks on the deep learning-based approaches used with different complex graphical structures. Professor Niloy Ganguly from IIT Kharagpur talked about the modeling of molecules and crystals using graphs and generating new molecules, and predicting crystal properties when combined with deep learning-based models. Continuing the discussions on graph neural networks (GNNs), Professor Stefanie Jegelka from MIT presented her work on improving the expressive power of GNNs by using the power of recursion and looking at graphs from a spectral perspective. In practice, models that can be scaled to learn embeddings for very large graphs are needed. Srinivasan Parthasarthy, professor at Ohio State University presented his work on scaling graph representation learning algorithms in an implementation agnostic fashion. Another variant of neural network architecture, based on algebraic topology was presented by our keynote speaker, Santiago Segarra, assistant professor at RICE University. Professor Segarra demonstrated the effectiveness of this architecture in extrapolating trajectories on synthetic and real datasets, with particular emphasis on the gains in generalizability to unseen trajectories.

Poster Session

In addition to the talks, there were many high-quality submissions to the workshop. Our program committee consisted of more than 60 researchers with diverse areas of expertise. All the paper submissions received at least three, and many of them got five, constructive reviews. Based on the reviews, 14 high-quality papers were accepted. Authors of full papers presented their works, and authors of short papers/extended abstracts presented their work in the poster session.

Panel Discussion

The workshop concluded with a panel discussion among the keynote speakers on “Learning and Reasoning with Complex graphs – a multi-disciplinary challenge.” The discussion brought up major challenges in the area, such as learning-based vs. model-driven approaches and their applications in complex networks. The panelists shared their perspectives on such topics, which sparked interesting debates. The panelists also gave suggestions for inspiring researchers working on interdisciplinary problems.

All the keynote talks and panel discussion are uploaded on our YouTube channel.

Website | Twitter | YouTube

tags: ,

AIhub is dedicated to free high-quality information about AI.
AIhub is dedicated to free high-quality information about AI.

            AIhub is supported by:

Related posts :

AIhub monthly digest: November 2023 – deconstructing sentiment analysis, few-shot learning for medical images, and Angry Birds structure generation

Welcome to our monthly digest, where you can catch up with AI research, events and news from the month past.
29 November 2023, by

An introduction to science communication at #NeurIPS2023

Find out more about our short course to be held in-person at NeurIPS on Monday 11 December.
28 November 2023, by

Co-creating better images of AI

In July, 2023, Science Gallery London and the London Office of Technology and Innovation co-hosted a workshop helping Londoners think about the kind of AI they want.
27 November 2023, by

The power of collaboration: power grid control with multi-agent reinforcement learning

A promising AI tool for assisting network operators in their real-time decision-making and operations

Goal representations for instruction following

How can we reconcile the ease of specifying tasks through natural language-based approaches with the performance improvements of goal-conditioned learning?
23 November 2023, by

A comprehensive survey on rare event prediction

We review the rare event prediction literature and highlight open research questions and future directions in the field.

©2021 - Association for the Understanding of Artificial Intelligence


©2021 - ROBOTS Association