arXiv research

Federated learning has become increasingly important for modern machine learning, especially for data privacy-sensitive scenarios. Existing federated learning mostly adopts the central server-based architecture or centralized architecture. However, in many social network scenarios, centralized federated learning is not…

Paper proves CLTs for Q-learning with asynchronous updates.

Mime algorithm improves federated learning by adapting centralized methods.

Decentralized learning achieves centralized performance via Gibbs measures.

This thesis tackles FL challenges with new methods and algorithms.

The goal of this research project is to analyze the dynamics of social networks using machine learning techniques to locate maximal cliques and to find clusters for the purpose of identifying a target demographic. Unsupervised machine learning techniques are designed and implemented in this project to analyze a dataset…

Many modern datasets can be represented as graphs and hence spectral decompositions such as graph principal component analysis (PCA) can be useful. Distinct from previous graph decomposition approaches based on subspace projection of a single topological feature, e.g., the Fiedler vector of centered graph adjacency mat…

FUSE neural centrality framework improves data point measurement in high dimensions.

Paper introduces input perturbation for privacy in machine learning models.

The speed with which a learning algorithm converges as it is presented with more data is a central problem in machine learning --- a fast rate of convergence means less data is needed for the same level of performance. The pursuit of fast rates in online and statistical learning has led to the discovery of many conditi…

Network metrics form a fundamental part of the network analysis toolbox. Used to quantitatively measure different aspects of the network, these metrics can give insights into the underlying network structure and function. In this work, we connect network metrics to modern probabilistic machine learning. We focus on the…

The paper develops a new theory to understand deep learning optimization.

Many functions of interest are in a high-dimensional space but exhibit low-dimensional structures. This paper studies regression of a $s$-Hölder function $f$ in $\mathbb{R}^D$ which varies along a central subspace of dimension $d$ while $d\ll D$. A direct approximation of $f$ in $\mathbb{R}^D$ with an $\varepsilon$ acc…

Most distributed machine learning systems nowadays, including TensorFlow and CNTK, are built in a centralized fashion. One bottleneck of centralized algorithms lies on high communication cost on the central node. Motivated by this, we ask, can decentralized algorithms be faster than its centralized counterpart? Althoug…

Centrality, as a geometrical property of the collision, is crucial for the physical interpretation of nucleus-nucleus and proton-nucleus experimental data. However, it cannot be directly accessed in event-by-event data analysis. Common methods for centrality estimation in A-A and p-A collisions usually rely on a single…

A central machine is interested in estimating the underlying structure of a sparse Gaussian Graphical Model (GGM) from datasets distributed across multiple local machines. The local machines can communicate with the central machine through a wireless multiple access channel. In this paper, we are interested in designin…

FSL-BDP models time-to-default without centralizing data, improving privacy mechanisms in federated settings.

Vertex centrality measures are a multi-purpose analysis tool, commonly used in many application environments to retrieve information and unveil knowledge from the graphs and network structural properties. However, the algorithms of such metrics are expensive in terms of computational resources when running real-time ap…

Algorithm reduces regret in distributed kernel bandits with shared randomness.

Communication is a key bottleneck in distributed training. Recently, an \emph{error-compensated} compression technology was particularly designed for the \emph{centralized} learning and receives huge successes, by showing significant advantages over state-of-the-art compression based methods in saving the communication…

The application of deep learning to symbolic domains remains an active research endeavour. Graph neural networks (GNN), consisting of trained neural modules which can be arranged in different topologies at run time, are sound alternatives to tackle relational problems which lend themselves to graph representations. In …

This work provides bounds on generalization error and privacy leakage in federated learning.

Access to sufficient annotated data is a common challenge in training deep neural networks on medical images. As annotating data is expensive and time-consuming, it is difficult for an individual medical center to reach large enough sample sizes to build their own, personalized models. As an alternative, data from all …

New centrality-based graph shift operators improve graph neural networks.

The paper introduces fixed-point centralities for networks and graphons.

Federated framework learns causal states to predict counterfactuals without centralizing data.

New algorithm reduces dimensionality in federated learning.

In this paper, we propose a data collaboration analysis method for distributed datasets. The proposed method is a centralized machine learning while training datasets and models remain distributed over some institutions. Recently, data became large and distributed with decreasing costs of data collection. If we can cen…

New framework for task-independent legged locomotion.

Study Q-learning with averaging for reinforcement learning, proving efficient inference and error bounds.

Federated learning (FL) is a machine learning setting where many clients (e.g. mobile devices or whole organizations) collaboratively train a model under the orchestration of a central server (e.g. service provider), while keeping the training data decentralized. FL embodies the principles of focused data collection an…

pFedGame uses game theory for decentralized federated learning in dynamic networks.

As relational datasets modeled as graphs keep increasing in size and their data-acquisition is permeated by uncertainty, graph-based analysis techniques can become computationally and conceptually challenging. In particular, node centrality measures rely on the assumption that the graph is perfectly known -- a premise …

The use of collaborative and decentralized machine learning techniques such as federated learning have the potential to enable the development and deployment of clinical risk predictions models in low-resource settings without requiring sensitive data be shared or stored in a central repository. This process necessitat…

Embedding graph nodes into a vector space can allow the use of machine learning to e.g. predict node classes, but the study of node embedding algorithms is immature compared to the natural language processing field because of a diverse nature of graphs. We examine the performance of node embedding algorithms with respe…

A new network-based high-level data classification method using betweenness centrality.

In an era where accumulating data is easy and storing it inexpensive, feature selection plays a central role in helping to reduce the high-dimensionality of huge amounts of otherwise meaningless data. In this paper, we propose a graph-based method for feature selection that ranks features by identifying the most import…

A hypersurface $M$ in $\mathbb{R}^n$, $n \geq 4$, has central ovaloid property if $M$ intersects some hyperplane transversally along an ovaloid and every such ovaloid on $M$ has central symmetry. We show that a complete, connected, smooth hypersurface with central ovaloid property must either be a cylinder over a centr…

The paper analyzes Q-learning convergence rates with asynchronous updates.

This paper addresses the problem of distributed detection in multi-agent networks. Agents receive private signals about an unknown state of the world. The underlying state is globally identifiable, yet informative signals may be dispersed throughout the network. Using an optimization-based framework, we develop an iter…

Central banks play a key role in promoting sustainable finance.

The purpose of this paper is to show how central extensions of (possibly infinite-dimensional) Lie algebras integrate to central extensions of étale Lie 2-groups. In finite dimensions, central extensions of Lie algebras integrate to central extensions of Lie groups, a fact which is due to the vanishing of π_2 for each …

A novel decentralized deep learning algorithm using gradient-based optimization.

Second-order guarantees for federated learning algorithms.

Optimal client sampling reduces communication in federated learning.

Coded Federated Learning speeds up model convergence by preemptively computing on parity data.

A new method selects important variables for clustering from dependency networks.

Constructs examples of centrally harmonic spaces and shows they are not generically harmonic.