433 citations · 1.3k across the 96 of their papers we have counts for
19 papers · 1 filter
Robust and Explainable Divide-and-Conquer Learning for Intrusion Detection
Yan Zhou, Kevin Hamlen, Michael De Lucia +5
Machine learning-based intrusion detection requires complex models to capture patterns in high-dimensional, noisy, and class-imbalanced raw network traffic, yet deploying such mode…
Regret Bounds for Reinforcement Learning from Multi-Source Imperfect Preferences
Ming Shi, Yingbin Liang, Ness B. Shroff +1
Reinforcement learning from human feedback (RLHF) replaces hard-to-specify rewards with pairwise trajectory preferences, yet regret-oriented theory often assumes that preference la…
FlowSymm: Physics Aware, Symmetry Preserving Graph Attention for Network Flow Completion
Ege Demirci, Francesco Bullo, Ananthram Swami +1
Recovering missing flows on the edges of a network, while exactly respecting local conservation laws, is a fundamental inverse problem that arises in many systems such as transport…
Mitigating Participation Imbalance Bias in Asynchronous Federated Learning
Xiangyu Chang, Manyi Yao, Srikanth V. Krishnamurthy +5
In Asynchronous Federated Learning (AFL), the central server immediately updates the global model with each arriving client's contribution. As a result, clients perform their local…
Fully Distributed Online Training of Graph Neural Networks in Networked Systems
Rostyslav Olshevskyi, Zhongyuan Zhao, Kevin Chan +3
Graph neural networks (GNNs) are powerful tools for developing scalable, decentralized artificial intelligence in large-scale networked systems, such as wireless networks, power gr…
Plug-and-Play Transformer Modules for Test-Time Adaptation
Xiangyu Chang, Sk Miraj Ahmed, Srikanth V. Krishnamurthy +4
Parameter-efficient tuning (PET) methods such as LoRA, Adapter, and Visual Prompt Tuning (VPT) have found success in enabling adaptation to new domains by tuning small modules with…
FLASH: Federated Learning Across Simultaneous Heterogeneities
Xiangyu Chang, Sk Miraj Ahmed, Srikanth V. Krishnamurthy +4
The key premise of federated learning (FL) is to train ML models across a diverse set of data-owners (clients), without exchanging local data. An overarching challenge to this date…
Learning to Transmit with Provable Guarantees in Wireless Federated Learning
Boning Li, Jake Perazzone, Ananthram Swami +1
We propose a novel data-driven approach to allocate transmit power for federated learning (FL) over interference-limited wireless networks. The proposed method is useful in challen…
Power Allocation for Wireless Federated Learning using Graph Neural Networks
Boning Li, Ananthram Swami, Santiago Segarra
We propose a data-driven approach for power allocation in the context of federated learning (FL) over interference-limited wireless networks. The power policy is designed to maximi…
Free Energy Node Embedding via Generalized Skip-gram with Negative Sampling
Yu Zhu, Ananthram Swami, Santiago Segarra
A widely established set of unsupervised node embedding methods can be interpreted as consisting of two distinctive steps: i) the definition of a similarity matrix based on the gra…
Unsupervised Joint -node Graph Representations with Compositional Energy-Based Models
Leonardo Cotta, Carlos H. C. Teixeira, Ananthram Swami +1
Existing Graph Neural Network (GNN) methods that learn inductive unsupervised graph representations focus on learning node and edge representations by predicting observed edges in…
An Extension of Fano's Inequality for Characterizing Model Susceptibility to Membership Inference Attacks
Sumit Kumar Jha, Susmit Jha, Rickard Ewetz +4
Deep neural networks have been shown to be vulnerable to membership inference attacks wherein the attacker aims to detect whether specific input data were used to train the model.…
GraphCL: Contrastive Self-Supervised Learning of Graph Representations
Hakim Hafidi, Mounir Ghogho, Philippe Ciblat +1
We propose Graph Contrastive Learning (GraphCL), a general framework for learning node representations in a self supervised manner. GraphCL learns node embeddings by maximizing the…
SENSE: Semantically Enhanced Node Sequence Embedding
Swati Rallapalli, Liang Ma, Mudhakar Srivatsa +4
Effectively capturing graph node sequences in the form of vector embeddings is critical to many applications. We achieve this by (i) first learning vector embeddings of single grap…
Federated Learning for Coalition Operations
D. Verma, S. Calo, S. Witherspoon +8
Machine Learning in coalition settings requires combining insights available from data assets and knowledge repositories distributed across multiple coalition partners. In tactical…
Attribution-driven Causal Analysis for Detection of Adversarial Examples
Susmit Jha, Sunny Raj, Steven Lawrence Fernandes +5
Attribution methods have been developed to explain the decision of a machine learning model on a given input. We use the Integrated Gradient method for finding attributions to defi…
Adversarial Perturbations Against Real-Time Video Classification Systems
Shasha Li, Ajaya Neupane, Sujoy Paul +4
Recent research has demonstrated the brittleness of machine learning systems to adversarial perturbations. However, the studies have been mostly limited to perturbations on images…
Multi-Armed Bandits on Partially Revealed Unit Interval Graphs
Xiao Xu, Sattar Vakili, Qing Zhao +1
A stochastic multi-armed bandit problem with side information on the similarity and dissimilarity across different arms is considered. The action space of the problem can be repres…
Sparse Diffusion-Convolutional Neural Networks
James Atwood, Siddharth Pal, Don Towsley +1
The predictive power and overall computational efficiency of Diffusion-convolutional neural networks make them an attractive choice for node classification tasks. However, a naive…