Skip to yearly menu bar Skip to main content

( events)   Timezone:  
Sat Jul 18 05:50 AM -- 02:30 PM (PDT)
Bridge Between Perception and Reasoning: Graph Neural Networks & Beyond
Jian Tang · Le Song · Jure Leskovec · Renjie Liao · Yujia Li · Sanja Fidler · Richard Zemel · Ruslan Salakhutdinov

Workshop Home Page

Deep learning has achieved great success in a variety of tasks such as recognizing objects in images, predicting the sentiment of sentences, or image/speech synthesis by training on a large-amount of data. However, most existing success are mainly focusing on perceptual tasks, which is also known as System I intelligence. In real world, many complicated tasks, such as autonomous driving, public policy decision making, and multi-hop question answering, require understanding the relationship between high-level variables in the data to perform logical reasoning, which is known as System II intelligence. Integrating system I and II intelligence lies in the core of artificial intelligence and machine learning.

Graph is an important structure for System II intelligence, with the universal representation ability to capture the relationship between different variables, and support interpretability, causality, and transferability / inductive generalization. Traditional logic and symbolic reasoning over graphs has relied on methods and tools which are very different from deep learning models, such Prolog language, SMT solvers, constrained optimization and discrete algorithms. Is such a methodology separation between System I and System II intelligence necessary? How to build a flexible, effective and efficient bridge to smoothly connect these two systems, and create higher order artificial intelligence?

Graph neural networks, have emerged as the tool of choice for graph representation learning, which has led to impressive progress in many classification and regression problems such as chemical synthesis, 3D-vision, recommender systems and social network analysis. However, prediction and classification tasks can be very different from logic/symbolic reasoning.

Bits and pieces of evidence can be gleaned from recent literature, suggesting graph neural networks may be a general tool to make such a connection. For example, \cite{battaglia2018relational,barcelo2019logical} viewed graph neural networks as tools to incorporate explicitly logic reasoning bias. \cite{kipf2018neural} used graph neural network to reason about interacting systems,
\cite{yoon2018inference,zhang2020efficient} used neural networks for logic and probabilistic inference, \cite{hudson2019learning, hu2019language} used graph neural networks for reasoning on scene graphs for visual question reasoning, \cite{qu2019probabilistic} studied reasoning on knowledge graphs with graph neural networks, and \cite{khalil2017learning, xu2018powerful, velickovic2019neural, sato2019approximation} used graph neural networks for discrete graph algorithms. However, there can still be a long way to go for a satisfactory and definite answers on the ability of graph neural networks for automatically discovering logic rules, and conducting long-range multi-step complex reasoning in combination with perception inputs such as language, vision, spatial and temporal variation.

{\bf Can graph neural networks be the key bridge to connect System I and System II intelligence? Are there other more flexible, effective and efficient alternatives?} For instance, \citep{wang2019satnet} combined max satisfiability solver with deep learning, \citep{manhaeve2018deepproblog} combined directed graphical and Problog with deep learning, \citep{skryagin2020splog}~combined sum product network with deep learning, \citep{silver2019few,alet2019graph}~combined logic reasoning with reinforcement learning. How do these alternative methods compare with graph neural networks for being a bridge?

The goal of this workshop is to bring researchers from previously separate fields, such as deep learning, logic/symbolic reasoning, statistical relational learning, and graph algorithms, into a common roof to discuss this potential interface and integration between System I and System intelligence. By providing a venue for the confluence of new advances in theoretical foundations, models and algorithms, as well as empirical discoveries, new benchmarks and impactful applications,

Opening Remarks: Jian Tang & Le Song (Opening)
Keynote: Yoshua Bengio (Invited Talk)
Keynote: Yoshua Bengio (Q&A) (Q&A)
Invited Talk: Peter Battaglia (Invited Talk)
Invited Talk: Peter Battaglia (Q&A) (Q&A)
Spotlight Talk (1): Generating Programmatic Referring Expressions via Program Synthesis (Spotlight Talk)
Spotlight Talk (2): Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoning (Spotlight Talk)
Spotlight Talk (3): Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphs (Spotlight Talk)
Spotlight Talk (4): Barking up the right tree: an approach to search over molecule synthesis DAGs (Spotlight Talk)
Morning Poster Session (Poster)
Invited Talk: Zico Kolter (Invited Talk)
Invited Talk: Zico Kolter (Q&A) (Q&A)
Invited Talk: Tommi Jaakkola (Invited Talk)
Invited Talk: Tommi Jaakkola (Q&A) (Q&A)
Invited Talk 4: Luc De Raedt (Invited Talk)
Invited Talk 4: Luc De Raedt (Q&A) (Q&A)
Spotlight talk (5): Modeling the semantics of data sources with graph neural networks (Spotlight Talk)
Spotlight talk (6): SpatialSim: Recognizing Spatial Configurations of Objects with Graph Neural Networks (Spotlight Talk)
Spotlight Talk (7): Enhancing Neural Mathematical Reasoning by Abductive Combination with Symbolic Library (Spotlight Talk)
Spotlight Talk (8): Learning Retrosynthetic Planning with Chemical Reasoning (Spotlight Talk)
Afternoon Poster Session (Poster)
Invited Talk 5:Ferran Alet (Invited Talk)
Invited Talk 5:Ferran Alet (Q&A) (Q&A)
Invited Talk 6: Kristian Kersting (Invited Talk)
Invited Talk 6: Kristian Kersting (Q&A) (Q&A)
Concluding Remarks (Conclusion)