IBM Neuro-Symbolic AI Workshop 2022

Neuro-symbolic AI combines knowledge-driven symbolic AI and data-driven machine learning approaches.
In this workshop we will show our recent progress toward some of the most outstanding issues in today's AI:

Incorporation of complex domain knowledge into learning, including ways to ensure trusted behavior -- and vice versa, incorporation of learning to account for incomplete or imperfect knowledge Rigorous expressive reasoning which is 'soft' (handles uncertainty) while computationally practical Learning with many fewer examples through the use of knowledge Full explainability by construction, including the reasons the models make their decisions Natural language processing via this approach to achieve state-of-the-art results, including handling more complex examples than is possible with today's default AI. This workshop will include talks from IBM researchers and other academic AI experts. The speakers will share an overview of neuro-symbolic AI technologies, achievements to date, and future direction for the field. The workshop will also include a panel discussion on the future of AI and the possible role of neuro-symbolic AI approaches.

The variety of topics, presentation modalities, and stakeholders will allow the audience of this workshop to reflect on the best path to advance AI in a way that is at the same time scientifically inspiring, economically sustainable, and beneficial to society.

neuro-symbolic AI

A new era of AI is rapidly emerging: neuro-symbolic AI combines knowledge-driven, symbolic AI with more traditional data-driven machine learning approaches. IBM is a leader in the research and development of neuro-symbolic AI technologies and we invite graduate students, AI practitioners, and anyone interested in this emerging field to participate in the 2022 IBM Neuro-Symbolic AI Summer School, to take place online on August 8-9 of this year.

The Summer School is a follow-on to the IBM Neuro-Symbolic AI Workshop held online in January 2022 (http://ibm.biz/ns-wkshp), which showcased the breadth and depth of the work being done in this field at IBM and by our collaborators. Participation in the first workshop is not a prerequisite for attending this year’s Summer School. All talks in the Summer School are meant to be self-contained.

The key properties of a neuro-symbolic system include:

• Explainability by construction; the reasons a model makes its decisions should be open to inspection, without the need to do explanatory data analysis;
• Learning with less and zero-shot learning; the system needs to be able to reason over the domain and over acquired knowledge;
• Generalization of the solutions to unseen tasks and unforeseen data distributions. IBM has demonstrated that natural language processing via the neuro-symbolic approach can achieve quantitatively and qualitatively state-of-the-art results, including handling more complex examples than is possible with today’s AI.

The summer school will include talks from over 25 IBMers in various areas of theory and the application of neuro-symbolic AI. We will also have a distinguished external speaker to share an overview of neuro-symbolic AI and its history. The agenda is a balance of educational content on neuro-symbolic AI and a discussion of recent results.

This is a virtual event and the registration for the event is free. The registered participants will get access to the recording of all sessions after the event.

Day 1 (August 8)

Session 1: Opening (08:30 - 10:30ET)

• Opening 20 minutes
  • Welcome (Alexander Gray - IBM)
  • Motivation and Objective (Francesca Rossi - IBM)
  • Summer School Overview (Jon Lenchner - IBM)
  • Neuro-Symbolic AI Essentials Badge (Asim Munawar - IBM)
• Neurosymbolic AI: The Third Wave (Artur d'Avila Garcez - City University of London) 1 hour
• IBM’s Perspective (Alexander Gray - IBM) 40 minutes

Session 2: Knowledge (11:00 - 13:00ET)

• Tutorial: Knowledge Foundations for AI Applications (Maria Chang - IBM) 1 hour

  • Knowledge Acquisition and Induction
  • Semantic Web
  • Logic for AI

• IBM Research Overview: Knowledge

• Part 1: Universal Logic Knowledge Base (Rosario Uceda-Sosa - IBM) 25 minutes

  • Interlinked KBs for broad encyclopedic, linguistic, and commonsense knowledge
  • Supporting foundation for neuro-symbolic reasoning

• Part 2: ULKB Logic Language (Guilherme Lima - IBM) 25 minutes

  • Higher order logic and simple type theory
  • The ULKB Logic Language and its Python API

• Part 3: Deep linguistic processing (Alexandre Rademaker - IBM) 10 minutes

  • Minimal recursive semantics and abstract meaning representation
  • Open source tooling

Session 3: Reasoning (13:30 - 15:30ET)

• Tutorial: A Very Brief Introduction to Logic and Reasoning (Achille Fokoue - IBM) 1 hour

  • First order logic (FOL) syntax and model-theoretic semantics
  • FOL reasoning and deductive systems
  • FOL Extensions

• IBM Research Overview: Learnable Reasoning (Ndivhuwo Makondo - IBM, Hima Karanam - IBM) 1 hour

  • Overview of Learning to Reason (e.g., neural theorem provers, MLNs, LTNs, etc)
  • Introduction to LNNs - our framework for Learnable Reasoning
  • Applications of LNNS

Session 4: Theory of Reasoning (16:00 - 18:00ET)

Tutorial: Theory of Reasoning

Foundations of Reasoning with Classical Logic (Marco Carmosino - IBM) 30 minutes

• Desiderata: what is logic, and what makes logic "good"?
• Example: First-Order Logic on finite graphs.
• Game-based semantics for First-Order Logic

Computational Complexity (Jon Lenchner - IBM) 30 minutes

• Time and Space Complexity: P vs. NP and Related Questions
• Descriptive Complexity
• Bridging from Descriptive Complexity to Time and Space Complexity via Games

IBM Research Overview: Complexity

Part I: Theory of Real-Valued Logics (Ron Fagin - IBM) 30 minutes

• Allowing sentences to take values other than “true” or “false”
• A rich class of real-valued logic sentences
• A sound and complete axiomatization

Part II: Games and Complexity Classes (Rik Sengupta - IBM) 30 minutes

• From Ehrenfecht-Fraisse Games to Multi-Structural Games
• From Multi-Structural Games to Syntactic Games
• Open Questions

Day 2 (August 9)

Session 1

• Tutorial: What can Transformers do? (Mark Wegman - IBM, Hans Florian - IBM) 1 hour 30 minutes
• Computational power of transformers
• What limits their power and what means there are around those limits?
• Theoretical power of a transformer and the relation to their behavior in practice

IBM Research Inductive Logic Programming with LNN (Prithviraj Sen - IBM, Sanjeeb Dash - IBM) 20 minutes Intro to Inductive Logic Programming (ILP) Generating LNNs for ILP Experimental ResAgendaItemDescts: Knowledge Base Completion (KBC) NS architecture zoo (Tengfei Ma - IBM, Ronny Luss - IBM) 10 minutes LNN for Times Series LNN for Mixed Models

Tutorial: NLP via Logic Deep Semantic Parsing with Abstract Meaning Representation (Ramon Astudillo - IBM) 30 minutes AMR as Deep Semantic Representation AMR parsing and AMR-to-text machine learning approaches Incorporating structure to Large Language Models for AMR parsing Entity Linking (Dinesh Garg - IBM) 30 minutes Setup: What do we mean by entity, mention, and linking Linking over knowledge graphs Linking over relational databases Challenges and Approaches for Reliable Reasoning with Foundation Models: An Abstractive Summarization Use-case (Pavan Kapanipathi - IBM, Hans Florian - IBM) 1 hour Reliable Reasoning with Foundation Models Abstractive Summarization: Reasoning and Factuality in Summarization Challenges and Neuro-Symbolic Approaches

Session 3: Sequential Decision Making (13:30 - 15:30ET)

Tutorial: SDM

Theory and practice of RL (Miao Liu - IBM) 30 minutes

• Core elements in RL
• Computational approaches and RL tools
• Important mechanisms - Hierarchical RL and Multiagent RL

Theory and practice of AI Planning (Michael Katz - IBM) 30 minutes

• What is planning and why is it hard
• Computational approaches to classical planning
• Planners and planning tools

IBM Research Overview: SDM

Integrating Planning and RL (Junkyu Lee - IBM) 30 minutes

• Introduction to integrating planning and RL
• AI Planning as annotation of RL
• Demonstration of libraries for planning annotated RL tasks

Logical optimal actions (Don Joven - IBM, Maxwell Crouse - IBM) 30 minutes

• Text-based games as an application environment
• LNN rule induction for learning world models
• The situation calculus and theorem proving applied to planning

Session 4: NS AI Toolkit (16:00 - 17:00ET)

Neuro-symbolic AI Toolkit (Naweed Khan - IBM) 45 minutes

• Logical Neural Networks (LNN)
• Universal Logic Knowledge Base (ULKB)
• Additional NSTK Components

Closing 15 minutes

• Badge, Feedback (Asim Munawar - IBM)
• Closing Remarks (Alexander Gray - IBM)