Temporal relational reasoning with neural networks

• Grant number: 17/24005-2
• Support Opportunities: Scholarships in Brazil - Doctorate
• Start date: April 01, 2018
• End date: October 31, 2020
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Ricardo da Silva Torres
• Grantee: Samuel Gomes Fadel
• Host Institution: Instituto de Computação (IC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
• Associated research grant: 16/50250-1 - The secret of playing football: Brazil versus the Netherlands, AP.TEM
• Associated scholarship(s): 18/19350-5 - Neural networks for temporal relational reasoning in soccer analysis, BE.EP.DR

Abstract

The study of relationships between objects and their properties is a common pattern in many areas of science.Studies on developmental disorders, gene expression analysis, and rumor propagation in social networks are some of the many examples where the analysis of graph data is fundamental to comprehending the phenomena in question.However, manually extracting and reasoning about this information quickly become a daunting undertaking once the number of connections and entities most of these phenomena involve is taken into account.Artificial neural networks (NNs) have recently been a central piece of many state-of-the-art machine learning methods, aimed exactly at dealing with large volumes of data.In particular, there has been an increasing interest in applying them to graph domains.Still, one important fact mostly unaccounted for is that almost all large real-world graphs evolve over time.In this research, we aim to identify relevant phenomena that can be represented as dynamic graphs and, in turn, to design neural network architectures that can be used to solve problems involving those phenomena.We adopt a methodology consisting of three stages for this.First, we establish baselines and comparisons for existing NNs designed for graph domains, since most of them were not directly compared to each other.We also take this opportunity to highlight which of those NNs also have a potential to be extended to dynamic graph domains.In the second stage, we extend those baselines by changing the domain to dynamic graphs.The third stage is concerned with tangible learning scenarios.For example, we expect to employ the developed methods in soccer match analysis.The reasoning for this is that many of the common learning tasks with graph data can be employed to soccer match analysis by modeling players as nodes (entities) and their interactions as edges (relationships).As a complex system of interactions, we expect that this leads to challenging problems not explored before.We expect, as a result of this research, NNs that successfully learn on dynamic graph domains.This will lead to contributions not only to machine learning, but also to other areas of science where we can represent a phenomenon with dynamic graphs. (AU)

Scientific publications

(4)

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

FADEL, SAMUEL G.; TORRES, RICARDO DA S.. Neural relational inference for disaster multimedia retrieval. MULTIMEDIA TOOLS AND APPLICATIONS, v. 79, n. 35-36, JUL 2020. (14/50715-9, 16/50250-1, 17/24005-2, 17/20945-0, 14/12236-1, 13/50169-1, 13/50155-0, 15/24494-8)

FADEL, SAMUEL G.; MAIR, SEBASTIAN; DA SILVA TORRES, RICARDO; BREFELD, ULF. Contextual movement models based on normalizing flows. AStA-Advances in Statistical Analysis, AUG 2021. (17/24005-2, 16/50250-1, 15/24494-8, 17/20945-0, 18/19350-5, 19/17729-0)

WERNECK, RAFAEL DE O.; DOURADO, ICARO C.; FADEL, SAMUEL G.; TABBONE, SALVATORE; TORRES, RICARDO DA S.; IEEE. GRAPH-BASED EARLY-FUSION FOR FLOOD DETECTION. 2018 25TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), v. N/A, p. 5-pg., 2018-01-01. (13/50169-1, 13/50155-0, 14/12236-1, 16/18429-1, 14/50715-9, 17/16453-5, 17/24005-2)

FADEL, SAMUEL G.; MAIR, SEBASTIAN; TORRES, RICARDO DA S.; BREFELD, ULF; OLIVER, N; PEREZCRUZ, F; KRAMER, S; READ, J; LOZANO, JA. Principled Interpolation in Normalizing Flows. MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2021: RESEARCH TRACK, PT II, v. 12976, p. 16-pg., 2021-01-01. (17/24005-2, 18/19350-5)

Academic Publications

(References retrieved automatically from State of São Paulo Research Institutions)

FADEL, Samuel Gomes. Aprendizado em domínios não-euclidianos: de grafos à modelagem generativa. 2021. Doctoral Thesis - Universidade Estadual de Campinas (UNICAMP). Instituto de Computação Campinas, SP.