Related papers: Transferable and Distributed User Association Poli…

Understanding how information propagates in real-life complex networks yields a better understanding of dynamic processes such as misinformation or epidemic spreading. The recently introduced branch of machine learning methods for learning…

We study real-time sampling and estimation of autoregressive Markovian sources in decentralized and dynamic multi-hop networks that share similar structures. Nodes cache neighboring samples and communicate over wireless collision channels.…

Software-defined networking (SDN) is the concept of decoupling the control and data planes to create a flexible and agile network, assisted by a central controller. However, the performance of SDN highly depends on the limitations in the…

Graph neural networks (GNNs) have been attracting increasing popularity due to their simplicity and effectiveness in a variety of fields. However, a large number of labeled data is generally required to train these networks, which could be…

We apply diffusion strategies to develop a fully-distributed cooperative reinforcement learning algorithm in which agents in a network communicate only with their immediate neighbors to improve predictions about their environment. The…

This paper explores a new research problem of unsupervised transfer learning across multiple spatiotemporal prediction tasks. Unlike most existing transfer learning methods that focus on fixing the discrepancy between supervised tasks, we…

Two of the most challenging goals to be achieved in the fifth generation (5G) and beyond communication are massive connectivity and higher capacity. The use of traditional orthogonal multiple access techniques limits the number of users…

Given an algorithmic predictor that is accurate on some source population consisting of strategic human decision subjects, will it remain accurate if the population respond to it? In our setting, an agent or a user corresponds to a sample…

Transfer learning is a machine learning paradigm where knowledge from one problem is utilized to solve a new but related problem. While conceivable that knowledge from one task could be useful for solving a related task, if not executed…

The problem of learning simultaneously several related tasks has received considerable attention in several domains, especially in machine learning with the so-called multitask learning problem or learning to learn problem [1], [2].…

This paper presents an adaptive combination strategy for distributed learning over diffusion networks. Since learning relies on the collaborative processing of the stochastic information at the dispersed agents, the overall performance can…

Modern systems (e.g., deep neural networks, big data analytics, and compilers) are highly configurable, which means they expose different performance behavior under different configurations. The fundamental challenge is that one cannot…

With the recent emergence of 5G era, heterogeneous cellular networks (HCNs) have invoked a popular research interest. In this paper, we provide a comprehensive analysis for multiantenna transmissions in a multi-tier downlink HCN. We first…

As next generation cellular networks become denser, associating users with the optimal base stations at each time while ensuring no base station is overloaded becomes critical for achieving stable and high network performance. We propose…

Transfer learning of prediction models has been extensively studied, while the corresponding policy learning approaches are rarely discussed. In this paper, we propose principled approaches for learning the optimal policy in the target…

Cache-aided wireless device-to-device (D2D) networks allow significant throughput increase, depending on the concentration of the popularity distribution of files. Many studies assume that all users have the same preference distribution;…

In most applications of utilizing neural networks for mathematical optimization, a dedicated model is trained for each specific optimization objective. However, in many scenarios, several distinct yet correlated objectives or tasks often…

Conventional transfer learning leverages weights of pre-trained networks, but mandates the need for similar neural architectures. Alternatively, knowledge distillation can transfer knowledge between heterogeneous networks but often requires…

Machine learning is used for inference and decision making in wearable sensor systems. However, recent studies have found that machine learning algorithms are easily fooled by the addition of adversarial perturbations to their inputs. What…

Transfer Learning aims to optimally aggregate samples from a target distribution, with related samples from a so-called source distribution to improve target risk. Multiple procedures have been proposed over the last two decades to address…