no code implementations • 7 Mar 2024 • Obaid Ullah Ahmad, Anwar Said, Mudassir Shabbir, Waseem Abbas, Xenofon Koutsoukos
In this paper, we study the problem of unsupervised graph representation learning by harnessing the control properties of dynamical networks defined on graphs.
1 code implementation • 10 Oct 2023 • Anwar Said, Mudassir Shabbir, Tyler Derr, Waseem Abbas, Xenofon Koutsoukos
The superior performance of GNNs often correlates with the availability and quality of node-level features in the input networks.
no code implementations • 23 Aug 2023 • Anwar Said, Tyler Derr, Mudassir Shabbir, Waseem Abbas, Xenofon Koutsoukos
By laying a solid foundation and fostering continued progress, this survey seeks to inspire researchers to further advance the field of graph unlearning, thereby instilling confidence in the ethical growth of AI systems and reinforcing the responsible application of machine learning techniques in various domains.
1 code implementation • NeurIPS 2023 • Anwar Said, Roza G. Bayrak, Tyler Derr, Mudassir Shabbir, Daniel Moyer, Catie Chang, Xenofon Koutsoukos
We delve deeply into the dataset generation search space by crafting 35 datasets that encompass static and dynamic brain connectivity, running in excess of 15 baseline methods for benchmarking.
1 code implementation • 6 Jun 2023 • Abihith Kothapalli, Mudassir Shabbir, Xenofon Koutsoukos
The minimum dominating set problem seeks to find a dominating set of minimum cardinality and is a well-established NP-hard combinatorial optimization problem.
no code implementations • 23 May 2023 • Ammar Ahmed, Anwar Said, Mudassir Shabbir, Xenofon Koutsoukos
However, this task is rather challenging owing to the absence of reliable and adequately managed datasets and learning models.
2 code implementations • 10 Mar 2023 • Ho Hin Lee, Quan Liu, Shunxing Bao, Qi Yang, Xin Yu, Leon Y. Cai, Thomas Li, Yuankai Huo, Xenofon Koutsoukos, Bennett A. Landman
We hypothesize that convolution with LK sizes is limited to maintain an optimal convergence for locality learning.
1 code implementation • 16 Mar 2022 • Feiyang Cai, Zhenkai Zhang, Jie Liu, Xenofon Koutsoukos
However, in a more realistic open set scenario, traditional classifiers with incomplete knowledge cannot tackle test data that are not from the training classes.
no code implementations • 7 Oct 2021 • Dimitrios Boursinos, Xenofon Koutsoukos
Machine learning components such as deep neural networks are used extensively in Cyber-Physical Systems (CPS).
no code implementations • 7 Oct 2021 • Dimitrios Boursinos, Xenofon Koutsoukos
In this paper, we use the Inductive Venn Predictors framework for computing probability intervals regarding the correctness of each prediction in real-time.
no code implementations • 7 Oct 2021 • Dimitrios Boursinos, Xenofon Koutsoukos
In this paper, we utilize a feedback loop between learning-enabled components used for classification and the sensors of an autonomous system in order to improve the confidence of the predictions.
no code implementations • 13 May 2021 • Waseem Abbas, Mudassir Shabbir, Yasin Yazicioglu, Xenofon Koutsoukos
In this paper, we study the maximum edge augmentation problem in directed Laplacian networks to improve their robustness while preserving lower bounds on their strong structural controllability (SSC).
no code implementations • 14 Apr 2021 • Feiyang Cai, Ali I. Ozdagli, Xenofon Koutsoukos
Cyber-physical systems (CPSs) use learning-enabled components (LECs) extensively to cope with various complex tasks under high-uncertainty environments.
1 code implementation • NeurIPS 2020 • Jiani Li, Waseem Abbas, Xenofon Koutsoukos
We analyze the approach for convex models and show that normal agents converge resiliently towards the global minimum. Further, aggregation with the proposed weight assignment rule always results in an improved expected regret than the non-cooperative case.
no code implementations • 21 Mar 2020 • Feiyang Cai, Jiani Li, Xenofon Koutsoukos
Learning-enabled components (LECs) are widely used in cyber-physical systems (CPS) since they can handle the uncertainty and variability of the environment and increase the level of autonomy.
1 code implementation • 11 Mar 2020 • Waseem Abbas, Mudassir Shabbir, Jiani Li, Xenofon Koutsoukos
In this paper, we study the resilient vector consensus problem in networks with adversarial agents and improve resilience guarantees of existing algorithms.
no code implementations • 11 Mar 2020 • Dimitrios Boursinos, Xenofon Koutsoukos
Cyber-physical systems (CPS) can benefit by the use of learning enabled components (LECs) such as deep neural networks (DNNs) for perception and decision making tasks.
no code implementations • 28 Jan 2020 • Feiyang Cai, Xenofon Koutsoukos
The simulation results show very small number of false positives and detection delay while the execution time is comparable to the execution time of the original machine learning components.
no code implementations • 14 Jan 2020 • Dimitrios Boursinos, Xenofon Koutsoukos
In this paper, we investigate how to use the conformal prediction framework for assurance monitoring of CPS with machine learning components.
no code implementations • 8 Sep 2019 • Mudassir Shabbir, Waseem Abbas, A. Yasin Yazicioglu, Xenofon Koutsoukos
The bound is based on a sequence of vectors containing the distances between leaders (nodes with external inputs) and followers (remaining nodes) in the underlying network graph.
no code implementations • 30 Apr 2018 • Amin Ghafouri, Yevgeniy Vorobeychik, Xenofon Koutsoukos
Attacks in cyber-physical systems (CPS) which manipulate sensor readings can cause enormous physical damage if undetected.
no code implementations • 8 Feb 2017 • Amin Ghafouri, Aron Laszka, Abhishek Dubey, Xenofon Koutsoukos
Erroneous data can adversely affect applications such as route planning, and can cause increased travel time.