32 citations · 140 across the 32 of their papers we have counts for
9 papers · 1 filter
Efficient and Stable Fully Dynamic Facility Location
Sayan Bhattacharya, Silvio Lattanzi, Nikos Parotsidis
We consider the classic facility location problem in fully dynamic data streams, where elements can be both inserted and deleted. In this problem, one is interested in maintaining…
On Classification Thresholds for Graph Attention with Edge Features
Kimon Fountoulakis, Dake He, Silvio Lattanzi +3
The recent years we have seen the rise of graph neural networks for prediction tasks on graphs. One of the dominant architectures is graph attention due to its ability to make pred…
Active Learning of Classifiers with Label and Seed Queries
Marco Bressan, Nicolò Cesa-Bianchi, Silvio Lattanzi +2
We study exact active learning of binary and multiclass classifiers with margin. Given an -point set , we want to learn any unknown classifier on who…
Deletion Robust Non-Monotone Submodular Maximization over Matroids
Paul Dütting, Federico Fusco, Silvio Lattanzi +2
Maximizing a submodular function is a fundamental task in machine learning and in this paper we study the deletion robust version of the problem under the classic matroids constrai…
TF-GNN: Graph Neural Networks in TensorFlow
Oleksandr Ferludin, Arno Eigenwillig, Martin Blais +24
TensorFlow-GNN (TF-GNN) is a scalable library for Graph Neural Networks in TensorFlow. It is designed from the bottom up to support the kinds of rich heterogeneous graph data that…
Approximating Dasgupta Cost in Sublinear Time from a Few Random Seeds
Michael Kapralov, Akash Kumar, Silvio Lattanzi +2
Testing graph cluster structure has been a central object of study in property testing since the foundational work of Goldreich and Ron [STOC'96] on expansion testing, i.e. the pro…
Scalable Differentially Private Clustering via Hierarchically Separated Trees
Vincent Cohen-Addad, Alessandro Epasto, Silvio Lattanzi +5
We study the private -median and -means clustering problem in dimensional Euclidean space. By leveraging tree embeddings, we give an efficient and easy to implement algor…
Near-Optimal Correlation Clustering with Privacy
Vincent Cohen-Addad, Chenglin Fan, Silvio Lattanzi +4
Correlation clustering is a central problem in unsupervised learning, with applications spanning community detection, duplicate detection, automated labelling and many more. In the…
Deletion Robust Submodular Maximization over Matroids
Paul Dütting, Federico Fusco, Silvio Lattanzi +2
Maximizing a monotone submodular function is a fundamental task in machine learning. In this paper, we study the deletion robust version of the problem under the classic matroids c…