39 citations · 130 across the 45 of their papers we have counts for
20 papers · 1 filter
RAD: Rule-Augmented Relational Anomaly Detection
Noah Dahle, Anne Tumlin, Ngoc Tran +2
Anomaly detection is often applied to data stored in relational databases, yet most existing methods require flattening multiple tables into a single feature matrix. This flattenin…
Defining and Benchmarking a Data-Centric Design Space for Brain Graph Construction
Qinwen Ge, Roza G. Bayrak, Anwar Said +3
The construction of brain graphs from functional Magnetic Resonance Imaging (fMRI) data plays a crucial role in enabling graph machine learning for neuroimaging. However, current p…
Feature Construction Using Network Control Theory and Rank Encoding for Graph Machine Learning
Anwar Said, Yifan Wei, Obaid Ullah Ahmad +3
In this article, we utilize the concept of average controllability in graphs, along with a novel rank encoding method, to enhance the performance of Graph Neural Networks (GNNs) in…
Robust Anomaly Detection with Graph Neural Networks using Controllability
Yifan Wei, Anwar Said, Waseem Abbas +1
Anomaly detection in complex domains poses significant challenges due to the need for extensive labeled data and the inherently imbalanced nature of anomalous versus benign samples…
Learning Backbones: Sparsifying Graphs through Zero Forcing for Effective Graph-Based Learning
Obaid Ullah Ahmad, Anwar Said, Mudassir Shabbir +2
This paper introduces a novel framework for graph sparsification that preserves the essential learning attributes of original graphs, improving computational efficiency and reducin…
PropEnc: A Property Encoder for Graph Neural Networks
Anwar Said, Waseem Abbas, Xenofon Koutsoukos
Graph machine learning, particularly using graph neural networks, heavily relies on node features. However, many real-world systems, such as social and biological networks, lack no…
Improving Graph Machine Learning Performance Through Feature Augmentation Based on Network Control Theory
Anwar Said, Obaid Ullah Ahmad, Waseem Abbas +2
Network control theory (NCT) offers a robust analytical framework for understanding the influence of network topology on dynamic behaviors, enabling researchers to decipher how cer…
Control-based Graph Embeddings with Data Augmentation for Contrastive Learning
Obaid Ullah Ahmad, Anwar Said, Mudassir Shabbir +2
In this paper, we study the problem of unsupervised graph representation learning by harnessing the control properties of dynamical networks defined on graphs. Our approach introdu…
A Survey of Graph Unlearning
Anwar Said, Ngoc N. Tran, Yuying Zhao +4
Graph unlearning emerges as a crucial advancement in the pursuit of responsible AI, providing the means to remove sensitive data traces from trained models, thereby upholding the \…
Learning-Based Heuristic for Combinatorial Optimization of the Minimum Dominating Set Problem using Graph Convolutional Networks
Abihith Kothapalli, Mudassir Shabbir, Xenofon Koutsoukos
A dominating set of a graph is a subset of vertices such that every vertex outside the dominating set is…
NeuroGraph: Benchmarks for Graph Machine Learning in Brain Connectomics
Anwar Said, Roza G. Bayrak, Tyler Derr +4
Machine learning provides a valuable tool for analyzing high-dimensional functional neuroimaging data, and is proving effective in predicting various neurological conditions, psych…
Reliable Probability Intervals For Classification Using Inductive Venn Predictors Based on Distance Learning
Dimitrios Boursinos, Xenofon Koutsoukos
Deep neural networks are frequently used by autonomous systems for their ability to learn complex, non-linear data patterns and make accurate predictions in dynamic environments. H…
Improving Prediction Confidence in Learning-Enabled Autonomous Systems
Dimitrios Boursinos, Xenofon Koutsoukos
Autonomous systems use extensively learning-enabled components such as deep neural networks (DNNs) for prediction and decision making. In this paper, we utilize a feedback loop bet…
Assurance Monitoring of Learning Enabled Cyber-Physical Systems Using Inductive Conformal Prediction based on Distance Learning
Dimitrios Boursinos, Xenofon Koutsoukos
Machine learning components such as deep neural networks are used extensively in Cyber-Physical Systems (CPS). However, such components may introduce new types of hazards that can…
Detection of Dataset Shifts in Learning-Enabled Cyber-Physical Systems using Variational Autoencoder for Regression
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. However, the dataset shifts…
Byzantine Resilient Distributed Multi-Task Learning
Jiani Li, Waseem Abbas, Xenofon Koutsoukos
Distributed multi-task learning provides significant advantages in multi-agent networks with heterogeneous data sources where agents aim to learn distinct but correlated models sim…
Trusted Confidence Bounds for Learning Enabled Cyber-Physical Systems
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. However, DNN…
Detecting Adversarial Examples in Learning-Enabled Cyber-Physical Systems using Variational Autoencoder for Regression
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 o…
Real-time Out-of-distribution Detection in Learning-Enabled Cyber-Physical Systems
Feiyang Cai, Xenofon Koutsoukos
Cyber-physical systems (CPS) greatly benefit by using machine learning components that can handle the uncertainty and variability of the real-world. Typical components such as deep…
Assurance Monitoring of Cyber-Physical Systems with Machine Learning Components
Dimitrios Boursinos, Xenofon Koutsoukos
Machine learning components such as deep neural networks are used extensively in Cyber-Physical Systems (CPS). However, they may introduce new types of hazards that can have disast…