Brazil

Performing analytical tasks over graph data has become increasingly interesting due to the ubiquity and large availability of relational information. However, unlike images or sentences, there is no notion of sequence in networks. Nodes (and edges) follow no absolute order, and it is hard for traditional machine learning (ML) algorithms to recognize a pattern and generalize their predictions on this type of
data. Graph Neural Networks (GNN) successfully tackled this problem. They became popular after the generalization of the convolution concept to the graph domain. However, they possess a large number of hyperparameters and their design and optimization is currently hand-made, based on heuristics or empirical intuition. Neural Architecture Search (NAS) methods appear as an interesting solution to this problem. In this direction, this paper compares two NAS methods for optimizing GNN: one based on reinforcement learning and a second based on evolutionary algorithms. Results consider 7 datasets over two search spaces and show that both methods obtain similar accuracies to a random search, raising the question of how many of the search space dimensions are actually relevant to the problem.

BRACIS 2020

Neural Architecture Search in Graph Neural Networks

evolutionary algorithms

neural architecture search

graph neural networks

reinforcement learning

The 9th Brazilian Conference on Intelligent Systems (BRACIS), the 16h Encontro Nacional de Inteligência Artificial e Computacional (ENIAC), and the 12th Concurso de Teses e Dissertações em Inteligência Artificial e Computacional (CTDIAC) was held from 20 to 23 October, 2020.

BRACIS originated from the combination of the two most important scientific events in Brazil in Artificial Intelligence (AI) and Computational Intelligence (CI): the Brazilian Symposium on Artificial Intelligence - SBIA (22 editions), and the Brazilian Symposium on Neural Networks - SBRN (13 editions). ENIAC is a national forum for researchers, practitioners, educators and students to present and discuss innovations, trends, experiences, developments and work in progress in the fields of Artificial and Computational Intelligence. CTDIAC is a satellite event whose goals are to disseminate and award the best dissertations and theses (MSc and PhDs concluded in Brazilian universities from June 2018 to May 2020) in Artificial and Computational Intelligence areas.

In this year, the Symposium on Knowledge Discovery, Mining and Learning (KDMiLe) will be held in conjunction with BRACIS 2020. This sysposium aims at integrating researchers, practitioners, developers, students and users to present their research results, to discuss ideas, and to exchange techniques, tools, and practical experiences – related to the Data Mining and Machine Learning areas.

technical paper

A major challenge in image classification tasks using Ma-chine Learning, and in particular when using deep neural networks, is domain shifting in deployment. This happens when images during usageare capture in different conditions from those used during training. In this paper, we show that despite previous works on the diagnosis of apple tree diseases using standard Convolutional Neural Networks displaying high accuracy, they do so only when no domain shift is present. When the trained model is asked to classify photos of apples taken in the wild, a 22% reduction in F1 score is observed. We propose to treat the task as a segmentation problem and test two different approaches, showing that using Mask R-CNN allows not only to improve performance in the original domain by 3%, but also significantly reduce losses in the new domain (only 6% reduction in F1 score). We establish segmentation as an important alternative towards improving diagnosis of apple tree diseases from photos.

Diagnosis of Apple Fruit Diseases in the Wildwith Mask R-CNN

This work presents a new hybrid method based on the route-first-cluster-second approach using Greedy Randomized Adaptive Search Procedure (GRASP), Differential Evolution (DE), Evolutionary Local Search (ELS) and set-partitioning problem (SPP) to solve well-known instances of Capacitated Vehicle Routing Problem (CVRP). The CVRP consists of minimizing the cost of a fleet of vehicles serving a set of customers from a single depot, in which every vehicle has the same capacity. The DE heuristic is used to build an initial feasible solution and ELS is applied until a local minimum is found during the local search phase of the GRASP. Finally, the SPP model provides a new optimal solution with regard to the built solutions in the GRASP. We perform computational experiments for benchmarks available in the literature and the results show that our method was effective to solve CVRP instances with a satisfactory performance. Moreover, a statistical test shows that there is not significant difference between the best known solutions of benchmark instances and the solutions of the proposed method.

A new hybridization of evolutionary algorithms, GRASP and set-partitioning formulation for the Capacitated Vehicle Routing Problem

The design of digital logic circuits involves transforming logical expressions into an electronic circuit seeking to minimize certain attributes such as the number of transistors. There are deterministic algorithms for this task, but they are limited to small problems. On the other hand metaheuristics can be used for solving this type of problem and Cartesian Genetic Programming (CGP) is widely adopted in the literature. In CGP, mutation is commonly the only operator for generating new candidate solutions. Thus, the performance of this metaheuristic is dependent on the proper choice of mutation and its parameters. Normally, CGP mutates the candidate solutions according to a uniform distribution. Thus, any modification has the same chance to occur. In order to improve the performance of CGP an adaptive mutation operator using an $\epsilon$-greedy strategy for bias the selection of gates is proposed here. The proposal is evaluated using problems of a benchmark from the literature. The results obtained indicate that the proposed adaptive mutation is promising and that its relative performance increases with the size of the problem.

A Reinforcement Learning Based Adaptive Mutation for Cartesian Genetic Programming Applied to the Design of Combinational Logic Circuits

Radiography is a primary examination used to diagnose chest conditions, as it is fast, low cost, and widely available. If the physician cannot conclude de diagnosis with the radiography, a computed tomography scan may be required. However, this exam is expensive and has low availability, mainly in the public health system of developing countries and low-income locations, which can delay the treatment and cause complications to the patient's health condition. Computer-aided diagnosis systems provide more resources for medical diagnostic decision-making, increasing the accuracy of the assessment of the patient's clinical condition. The main objective of this work is to develop a deep-learning-based approach that performs an automatic analysis of digital images of chest radiographs to aid the detection of pulmonary nodules and masses, aiming to extract sufficient relevant information from the image, optimizing the initial phase of the diagnosis of lung lesions.
The developed approach uses neural networks in a dataset of 8,178 annotated chest radiographs extracted from a public dataset. Half of it is of images annotated with "nodule" or "mass," and the other half is of images with "no findings." We implemented and tested convolutional neural networks and data preprocessing techniques to create a classification model.
A model with five convolution layers that achieved 0.72 accuracy, 0.75 sensitivity, and 0.68 specificity.
The proposed approach achieved results comparable to state of the art for lesion identification using limited computational power and can assist radiological practice as a second opinion, which can improve the rates of early diagnosed cancer.

A deep learning approach for pulmonary lesion identification in chest radiographs

The Cooperative Multi-Robot Observation of Multiple Moving Targets (CMOMMT) considers two types of robots, observers and targets, in a partially observable 2D environment, in which the task of the observers is to monitor the target robots under a limited radial range of the sensor, minimizing the total time the targets escape observation. The Cooperative Target Observation (CTO), a variant of the CMOMMT problem, considers the environment to be fully observable, where targets cooperate with observers by reporting their locations. These problems are at the center of many problems that occur in real-world wildlife research, crowd social movement, and surveillance situations. Regarding research related to the field of surveillance, this work proposes an approach to the extended CTO problem, what we call the COSTA problem: Cooperative Observation of Smart Target Agents. The approach employs genetic algorithm and recurrent deep neural networks to improve the performance of target robots and, therefore, to improve the research of new decision-making strategies in the context of observer robots. The first results were auspicious, as the average number of target evasion increased, considering the other recent approaches to the problem.

Cooperative Observation of Smart Target Agents

As Wireless Sensor Networks - WSNs are being used more and more in applications with high demand for the processing of videos and images, the processing load of the nodes also must be considered by energy-saving strategies. Usually, these strategies focused only on communication. The overloading of nodes can result in a degraded performance regarding the network lifetime and availability of the provided services. A few algorithms, based on heuristics, have been proposed in the literature to balance the load at the application level. These algorithms drawnback are the lack of quality assurance. Thus, this work presents a novel semi-distributed solution, applying techniques to solve Constraint Optimization Problem - COP on the load balancing in WSN. Our approach guarantee that all events are processed during the lifetime of the network and that there is a fixed number of exchanged messages per event, only reducing the lifetime of the network by an estimable time. Experimental results pointed out that the proposed approach allows the network, while alive, to sense all happened events each day, and its performance is better than the one achieved by the state-of-the-art for lower density networks.

Application-Level Load Balancing for Reactive Wireless Sensor Networks: An Approach Based on Constraint Optimization Problems

An effective way to deal with classification problems, among other approaches, is using Fuzzy Rule-Based Classification Systems (FRBCSs). These classification systems are mainly composed of two modules, the Knowledge Base (KB) and the Fuzzy Reasoning Method (FRM). The KB is responsible for storing information related to the problem, while the FRM performs the classification of new examples based on the KB. A key point in the FRM is how the information given by the triggered fuzzy rules is aggregated. Several FRMs have been proposed in the literature employing generalizations of the Choquet Integral as the aggregation function. The usage of this function to perform the aggregation is efficient because it uses fuzzy measures to model the interrelationships between the data. Indeed, the performance of the classification system is strongly related to the underlying fuzzy measure. However, many of those generalizations have used fuzzy measures that do not properly model the interaction between the data. In this context, we intend to enhance the way how the relationships between the rules are modeled in the FRM
of an FRBCS. In order to accomplish that, we propose the use of a well known fuzzy measure, the Sugeno lambda, as an alternative to the Power Measure, which is widely used in many generalizations of the Choquet Integral. The experimental evaluation shows statistical equivalent results comparing our method with the state-of-the-art fuzzy classifier.

An alternative to Power Measure for Fuzzy Rule-Based Classification Systems

The test phase is a crucial step to seek the correction of the entire software system to provide guarantees of operation and safety for users. However, applications based on multiagent systems have greater difficulty of being tested due to their properties such as autonomy, reactivity, pro-activity, and social skills. An organizational model imposes some restrictions on the behavior of agents since they are a set of behavioral constraints. This paper presents a method for systematic testing of multiagent systems specified under the Moise+ organizational model. First, a mapping is performed on a colored Petri net to measure the number of test cases needed to verify the system using adequacy criteria called the state transition path. Then each test case is specified from the Petri Net model in detail to be used as a guide in a test environment. The results indicate that the methodology can measure the testability and generate use cases for a Moise+ specification, guaranteeing a correction degree for a social level of a multiagent system.

Testing Multiagent Systems under Organizational Model Moise using a Test Adequacy Criterion based on State Transition Path

Agent-based applications need to be able to explain their reasoning path that led them to adopt a given behavior. An integral part of practical intelligent agents is the goal selection, where the aim is to chose the goals that agents will commit to, so it is important to endow the agents with the ability to explain their decisions about the goals they have pursued or are pursuing. In this work we propose a method for generating explanations for the goal selection, which can be given to both to intelligent agents and human users.

An Argumentation-based Approach for Explaining Goal Selection in Intelligent Agents

Planning problems with continuous state and action spacesare difficult to solve with existing planning techniques, specially when the state transition is defined by a high-dimension non-linear dynamics. Recently, a technique called Planning through Backpropagation (PtB) was introduced as an efficient and scalable alternative to traditional optimization-based methods for continuous planning problems. PtB leverages modern gradient descent algorithms and highly optimized automatic differentiation libraries to obtain approximate solutions. However, to date there have been no empirical evaluations comparing PtB with Linear-Quadratic (LQ) control problems. In this work, we compare PtB with an optimal algorithm from control theory called LQR, and its iterative version iLQR, when solving linear and non-linear continuous deterministic planning problems. The empirical results suggest that PtB can be an efficient alternative to optimizing non-linear continuous deterministic planning, being much easier to be implemented and stabilized than classical model-predictive control methods.

Neural Architecture Search in Graph Neural Networks

Downloads

Next from BRACIS 2020

Diagnosis of Apple Fruit Diseases in the Wildwith Mask R-CNN

Similar lecture

Towards Heterogeneous Multi-Agent Reinforcement Learning with Graph Neural Networks

Neural Architecture Search in Graph Neural Networks

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from BRACIS 2020

Diagnosis of Apple Fruit Diseases in the Wildwith Mask R-CNN

Similar lecture

Towards Heterogeneous Multi-Agent Reinforcement Learning with Graph Neural Networks

Downloads