Search Results for author: Rik Sarkar

Found 26 papers, 15 papers with code

Towards Understanding the Interplay of Generative Artificial Intelligence and the Internet

1 code implementation8 Jun 2023 Gonzalo Martínez, Lauren Watson, Pedro Reviriego, José Alberto Hernández, Marc Juarez, Rik Sarkar

Our results show that the quality and diversity of the generated images can degrade over time suggesting that incorporating AI-created data can have undesired effects on future versions of generative models.

Metric Space Magnitude and Generalisation in Neural Networks

no code implementations9 May 2023 Rayna Andreeva, Katharina Limbeck, Bastian Rieck, Rik Sarkar

Deep learning models have seen significant successes in numerous applications, but their inner workings remain elusive.

Differentially Private Shapley Values for Data Evaluation

no code implementations1 Jun 2022 Lauren Watson, Rayna Andreeva, Hao-Tsung Yang, Rik Sarkar

The Shapley value has been proposed as a solution to many applications in machine learning, including for equitable valuation of data.

BIG-bench Machine Learning

On Cyclic Solutions to the Min-Max Latency Multi-Robot Patrolling Problem

no code implementations14 Mar 2022 Peyman Afshani, Mark De Berg, Kevin Buchin, Jie Gao, Maarten Loffler, Amir Nayyeri, Benjamin Raichel, Rik Sarkar, Haotian Wang, Hao-Tsung Yang

For the Euclidean version of the problem, for instance, combining our results with known results on Euclidean TSP, yields a PTAS for approximating an optimal cyclic solution, and it yields a $(2(1-1/k)+\varepsilon)$-approximation of the optimal unrestricted solution.

Continual and Sliding Window Release for Private Empirical Risk Minimization

no code implementations7 Mar 2022 Lauren Watson, Abhirup Ghosh, Benedek Rozemberczki, Rik Sarkar

One version of the algorithm uses the entire data history to improve the model for the recent window.

The Shapley Value in Machine Learning

2 code implementations11 Feb 2022 Benedek Rozemberczki, Lauren Watson, Péter Bayer, Hao-Tsung Yang, Olivér Kiss, Sebastian Nilsson, Rik Sarkar

Over the last few years, the Shapley value, a solution concept from cooperative game theory, has found numerous applications in machine learning.

BIG-bench Machine Learning Data Valuation +5

Euler Characteristic Surfaces

1 code implementation16 Feb 2021 Gabriele Beltramo, Rayna Andreeva, Ylenia Giarratano, Miguel O. Bernabeu, Rik Sarkar, Primoz Skraba

While topological data analysis of higher-dimensional parameter spaces using stronger invariants such as homology continues to be the subject of intense research, Euler characteristic is more manageable theoretically and computationally, and this analysis can be seen as an important intermediary step in multi-parameter topological data analysis.

Topological Data Analysis Algebraic Topology Computational Geometry

Twitch Gamers: a Dataset for Evaluating Proximity Preserving and Structural Role-based Node Embeddings

2 code implementations8 Jan 2021 Benedek Rozemberczki, Rik Sarkar

Proximity preserving and structural role-based node embeddings have become a prime workhorse of applied graph mining.

Graph Mining Node Classification

The Shapley Value of Classifiers in Ensemble Games

2 code implementations6 Jan 2021 Benedek Rozemberczki, Rik Sarkar

We argue that the Shapley value of models in these games is an effective decision metric for choosing a high performing subset of models from the ensemble.

Ensemble Pruning Graph Classification

Heterogeneous Interventions Reduce the Spread of COVID-19 in Simulations on Real Mobility Data

1 code implementation14 Aug 2020 Haotian Wang, Abhirup Ghosh, Jiaxin Ding, Rik Sarkar, Jie Gao

Major interventions have been introduced worldwide to slow down the spread of the SARS-CoV-2 virus.

Social and Information Networks Physics and Society

Stability Enhanced Privacy and Applications in Private Stochastic Gradient Descent

no code implementations25 Jun 2020 Lauren Watson, Benedek Rozemberczki, Rik Sarkar

Private machine learning involves addition of noise while training, resulting in lower accuracy.

feature selection

Little Ball of Fur: A Python Library for Graph Sampling

1 code implementation CIKM 2020 Benedek Rozemberczki, Oliver Kiss, Rik Sarkar

In this paper, we describe Little Ball of Fur a Python library that includes more than twenty graph sampling algorithms.

Graph Classification Graph Embedding +2

Characteristic Functions on Graphs: Birds of a Feather, from Statistical Descriptors to Parametric Models

3 code implementations CIKM 2020 Benedek Rozemberczki, Rik Sarkar

In this paper, we propose a flexible notion of characteristic functions defined on graph vertices to describe the distribution of vertex features at multiple scales.

Graph Classification Node Classification +1

Karate Club: An API Oriented Open-source Python Framework for Unsupervised Learning on Graphs

2 code implementations CIKM 2020 Benedek Rozemberczki, Oliver Kiss, Rik Sarkar

We present Karate Club a Python framework combining more than 30 state-of-the-art graph mining algorithms which can solve unsupervised machine learning tasks.

BIG-bench Machine Learning Clustering +5

Fast Sequence-Based Embedding with Diffusion Graphs

4 code implementations21 Jan 2020 Benedek Rozemberczki, Rik Sarkar

A graph embedding is a representation of graph vertices in a low-dimensional space, which approximately preserves properties such as distances between nodes.

Clustering Community Detection +2

Multi-scale Attributed Node Embedding

4 code implementations28 Sep 2019 Benedek Rozemberczki, Carl Allen, Rik Sarkar

We present network embedding algorithms that capture information about a node from the local distribution over node attributes around it, as observed over random walks following an approach similar to Skip-gram.

Network Embedding

Fast Sequence Based Embedding with Diffusion Graphs

2 code implementations CompleNet 2018 Benedek Rozemberczki, Rik Sarkar

A graph embedding is a representation of the vertices of a graph in a low dimensional space, which approximately preserves proper-ties such as distances between nodes.

Clustering Community Detection +3

GEMSEC: Graph Embedding with Self Clustering

3 code implementations ASONAM 2019 Benedek Rozemberczki, Ryan Davies, Rik Sarkar, Charles Sutton

In this paper we propose GEMSEC a graph embedding algorithm which learns a clustering of the nodes simultaneously with computing their features.

Social and Information Networks

Distributed Submodular Maximization

no code implementations3 Nov 2014 Baharan Mirzasoleiman, Amin Karbasi, Rik Sarkar, Andreas Krause

Such problems can often be reduced to maximizing a submodular set function subject to various constraints.


Cannot find the paper you are looking for? You can Submit a new open access paper.