Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Shafi, Zohair"'
Machine learning models for graphs in real-world applications are prone to two primary types of uncertainty: (1) those that arise from incomplete and noisy data and (2) those that arise from uncertainty of the model in its output. These sources of un
Externí odkaz:
http://arxiv.org/abs/2412.05735
Node embedding algorithms produce low-dimensional latent representations of nodes in a graph. These embeddings are often used for downstream tasks, such as node classification and link prediction. In this paper, we investigate the following two quest
Externí odkaz:
http://arxiv.org/abs/2406.07642
Autor:
Shafi, Zohair, Miller, Benjamin A., Chatterjee, Ayan, Eliassi-Rad, Tina, Caceres, Rajmonda S.
Recent advances in machine learning (ML) have shown promise in aiding and accelerating classical combinatorial optimization algorithms. ML-based speed ups that aim to learn in an end to end manner (i.e., directly output the solution) tend to trade of
Externí odkaz:
http://arxiv.org/abs/2310.07980
Machine learning (ML) approaches are increasingly being used to accelerate combinatorial optimization (CO) problems. We investigate the Set Cover Problem (SCP) and propose Graph-SCP, a graph neural network method that augments existing optimization s
Externí odkaz:
http://arxiv.org/abs/2310.07979
Autor:
Miller, Benjamin A., Shafi, Zohair, Ruml, Wheeler, Vorobeychik, Yevgeniy, Eliassi-Rad, Tina, Alfeld, Scott
Identifying shortest paths between nodes in a network is an important task in applications involving routing of resources. Recent work has shown that a malicious actor can manipulate a graph to make traffic between two nodes of interest follow their
Externí odkaz:
http://arxiv.org/abs/2305.19083
Autor:
Miller, Benjamin A., Shafi, Zohair, Ruml, Wheeler, Vorobeychik, Yevgeniy, Eliassi-Rad, Tina, Alfeld, Scott
Identifying shortest paths between nodes in a network is a common graph analysis problem that is important for many applications involving routing of resources. An adversary that can manipulate the graph structure could alter traffic patterns to gain
Externí odkaz:
http://arxiv.org/abs/2211.11141
Autor:
Chatterjee, Ayan, Walters, Robin, Shafi, Zohair, Ahmed, Omair Shafi, Sebek, Michael, Gysi, Deisy, Yu, Rose, Eliassi-Rad, Tina, Barabási, Albert-László, Menichetti, Giulia
Identifying novel drug-target interactions (DTI) is a critical and rate limiting step in drug discovery. While deep learning models have been proposed to accelerate the identification process, we show that state-of-the-art models fail to generalize t
Externí odkaz:
http://arxiv.org/abs/2112.13168
Autor:
Miller, Benjamin A., Shafi, Zohair, Ruml, Wheeler, Vorobeychik, Yevgeniy, Eliassi-Rad, Tina, Alfeld, Scott
Finding shortest paths in a given network (e.g., a computer network or a road network) is a well-studied task with many applications. We consider this task under the presence of an adversary, who can manipulate the network by perturbing its edge weig
Externí odkaz:
http://arxiv.org/abs/2107.03347
Autor:
Miller, Benjamin A., Shafi, Zohair, Ruml, Wheeler, Vorobeychik, Yevgeniy, Eliassi-Rad, Tina, Alfeld, Scott
Shortest paths in complex networks play key roles in many applications. Examples include routing packets in a computer network, routing traffic on a transportation network, and inferring semantic distances between concepts on the World Wide Web. An a
Externí odkaz:
http://arxiv.org/abs/2104.03761
We present RAWLSNET, a system for altering Bayesian Network (BN) models to satisfy the Rawlsian principle of fair equality of opportunity (FEO). RAWLSNET's BN models generate aspirational data distributions: data generated to reflect an ideally fair,
Externí odkaz:
http://arxiv.org/abs/2104.03909