publications

2023

1. CAMSAP

   Multi-Target Tracking with Transferable Convolutional Neural Networks

   Damian Owerko, Charilaos Kanatsoulis, Alejandro Ribeiro, and 2 more authors

   In 2023 9th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP) Jul 2023

   Abs Code

   Multi-target tracking (MTT) is a traditional signal processing task, where the goal is to estimate the states of an unknown number of moving targets from noisy sensor measurements. In this paper, we revisit MTT from a deep learning perspective and propose convolutional neural network (CNN) architectures to tackle it. We represent the target states and sensor measurements as images. Thereby we recast the problem as a image-to-image prediction task for which we train a fully convolutional model. This architecture is motivated by a novel theoretical bound on the transferability error of CNN. The proposed CNN architecture outperforms a GM-PHD filter on the MTT task with 10 targets. The CNN performance transfers without re-training to a larger MTT task with 250 targets with only a \13\% increase in average OSPA.

2. ACSSC

   Solving Large-scale Spatial Problems with Convolutional Neural Networks

   Damian Owerko, Charilaos I. Kanatsoulis, and Alejandro Ribeiro

   In 2023 54th Asilomar Conference on Signals, Systems, and Computers Jun 2023

   Abs Code

   Over the past decade, deep learning research has been accelerated by increasingly powerful hardware, which facilitated rapid growth in the model complexity and the amount of data ingested. This is becoming unsustainable and therefore refocusing on efficiency is necessary. In this paper, we employ transfer learning to improve training efficiency for large-scale spatial problems. We propose that a convolutional neural network (CNN) can be trained on small windows of signals, but evaluated on arbitrarily large signals with little to no performance degradation, and provide a theoretical bound on the resulting generalization error. Our proof leverages shift-equivariance of CNNs, a property that is underexploited in transfer learning. The theoretical results are experimentally supported in the context of mobile infrastructure on demand (MID). The proposed approach is able to tackle MID at large scales with hundreds of agents, which was computationally intractable prior to this work.

3. TSP

   Transferability of Convolutional Neural Networks in Stationary Learning Tasks

   Damian Owerko, Charilaos I. Kanatsoulis, Jennifer Bondarchuk, and 2 more authors

   Jul 2023

   Abs Code

   Recent advances in hardware and big data acquisition have accelerated the development of deep learning techniques. For an extended period of time, increasing the model complexity has led to performance improvements for various tasks. However, this trend is becoming unsustainable and there is a need for alternative, computationally lighter . In this paper, we introduce a novel framework for efficient training of convolutional neural networks (CNNs) for large-scale spatial problems. To accomplish this we investigate the properties of CNNs for tasks that the underlying signals are stationary and exhibit translational symmetries. We show that a CNN trained on small windows of such signals achieves a nearly identical zero-shot performance on much larger windows. This claim is supported by our theoretical analysis, which provides a bound on the performance degradation. Additionally, we conduct thorough experimental analysis on two tasks: multi-target tracking and mobile infrastructure on demand. Our results show that the CNN is able to tackle problems with many hundreds of agents after being trained with fewer than ten. Thus, CNN architectures provide solutions to these problems at previously computationally intractable scales.

2022

1. ICASSP

   Unsupervised Optimal Power Flow Using Graph Neural Networks

   Damian Owerko, Fernando Gama, and Alejandro Ribeiro

   Oct 2022

   Abs Code

   Optimal power flow (OPF) is a critical optimization problem that allocates power to the generators in order to satisfy the demand at a minimum cost. Solving this problem exactly is computationally infeasible in the general case. In this work, we propose to leverage graph signal processing and machine learning. More specifically, we use a graph neural network to learn a nonlinear parametrization between the power demanded and the corresponding allocation. We learn the solution in an unsupervised manner, minimizing the cost directly. In order to take into account the electrical constraints of the grid, we propose a novel barrier method that is differentiable and works on initially infeasible points. We show through simulations that the use of GNNs in this unsupervised learning context leads to solutions comparable to standard solvers while being computationally efficient and avoiding constraint violations most of the time.

2020

1. ICASSP

   Optimal Power Flow Using Graph Neural Networks

   Damian Owerko, Fernando Gama, and Alejandro Ribeiro

   In ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) May 2020

   Abs Code

   Optimal power flow (OPF) is one of the most important optimization problems in the energy industry. In its simplest form, OPF attempts to find the optimal power that the generators within the grid have to produce to satisfy a given demand. Optimality is measured with respect to the cost that each generator incurs in producing this power. The OPF problem is non-convex due to the sinusoidal nature of electrical generation and thus is difficult to solve. Using small angle approximations leads to a convex problem known as DC OPF, but this approximation is no longer valid when power grids are heavily loaded. Many approximate solutions have been since put forward, but these do not scale to large power networks. In this paper, we propose using graph neural networks (which are localized, scalable parametrizations of network data) trained under the imitation learning framework to approximate a given optimal solution. While the optimal solution is costly, it is only required to be computed for network states in the training set. During test time, the GNN adequately learns how to compute the OPF solution. Numerical experiments are run on the IEEE-30 and IEEE-118 test cases.

2018

1. GlobalSIP

   Predicting Power Outages Using Graph Neural Networks

   Damian Owerko, Fernando Gama, and Alejandro Ribeiro

   In 2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP) Nov 2018

   Abs

   Power outages have a major impact on economic development due to the dependence of (virtually all) productive sectors on electric power. Thus, many resources within the scientific and engineering communities have been employed to improve the efficiency and reliability of power grids. In particular, we consider the problem of predicting power outages based on the current weather conditions. Weather measurements taken by a sensor network naturally fit within the graph signal processing framework since the measurements are related by the relative position of the sensors. We deploy novel graph neural networks to adequately process weather measurements in order to determine the likelihood of a power outage. Tests on weather measurements taken in the region of New York City show a 1.04% error in the prediction.