Search Results for author:
Found 26 papers, 3 papers with code
Federated Clustering: An Unsupervised Cluster-Wise Training for Decentralized Data Distributions
Federated Learning (FL) is a pivotal approach in decentralized machine learning, especially when data privacy is crucial and direct data sharing is impractical.
FedQUIT: On-Device Federated Unlearning via a Quasi-Competent Virtual Teacher
Federated Learning (FL) promises better privacy guarantees for individuals' data when machine learning models are collaboratively trained.
Understanding and Addressing Gender Bias in Expert Finding Task
To the best of our knowledge, this study is the first to focus on detecting and mitigating gender bias in EF methods.
Leveraging Topic Specificity and Social Relationships for Expert Finding in Community Question Answering Platforms
The effectiveness of these platforms relies on their ability to identify and direct questions to the most knowledgeable users within the community, a process known as Expert Finding (EF).
Robustness of Decentralised Learning to Nodes and Data Disruption
Through these configurations, we are able to show the non-trivial interplay between the properties of the network connecting nodes, the persistence of knowledge acquired collectively before disruption or lack thereof, and the effect of data availability pre- and post-disruption.
Optimizing Risk-averse Human-AI Hybrid Teams
For hybrid teams, we will refer to both the humans and AI systems as agents.
Impact of network topology on the performance of Decentralized Federated Learning
We highlight the challenges in transferring knowledge from peripheral to central nodes, attributed to a dilution effect during model aggregation.
Optimizing Delegation in Collaborative Human-AI Hybrid Teams
The manager learns a model of behavior linking observations of agent performance and the environment/world the team is operating in, and from these observations makes the most desirable selection of a control agent.
Coordination-free Decentralised Federated Learning on Complex Networks: Overcoming Heterogeneity
Federated Learning (FL) is a well-known framework for successfully performing a learning task in an edge computing scenario where the devices involved have limited resources and incomplete data representation.
Exploring the Impact of Disrupted Peer-to-Peer Communications on Fully Decentralized Learning in Disaster Scenarios
Thus, fully decentralized learning can help in this case.
Optimizing delegation between human and AI collaborative agents
In the context of humans operating with artificial or autonomous agents in a hybrid team, it is essential to accurately identify when to authorize those team members to perform actions.
The effect of network topologies on fully decentralized learning: a preliminary investigation
Specifically, we highlight the different roles in this process of more or less connected nodes (hubs and leaves), as well as that of macroscopic network properties (primarily, degree distribution and modularity).
Human-AI Coevolution
Human-AI coevolution, defined as a process in which humans and AI algorithms continuously influence each other, increasingly characterises our society, but is understudied in artificial intelligence and complexity science literature.
Compensating for Sensing Failures via Delegation in Human-AI Hybrid Systems
In this context, the manager will estimate its best action based on the likelihood of either (human, autonomous) agent failure as a result of their sensing capabilities and possible deficiencies.
Anomaly Detection through Unsupervised Federated Learning
Experiments show that our method is robust, and it can detect communities consistent with the ideal partitioning in which groups of clients having the same inlier patterns are known.
Modeling Human Behavior Part II -- Cognitive approaches and Uncertainty
We will arrange these topics as follows (i) methods such as cognitive architectures, cognitive heuristics, and related which demonstrate assumptions of limitations on cognitive resources and how that impacts decisions and (ii) methods which generate and utilize representations of bias or uncertainty to model human decision-making or the future outcomes of decisions.
Modeling Human Behavior Part I -- Learning and Belief Approaches
To make this possible, autonomous agents will require the ability to embed practical models of human behavior, which allow them not only to replicate human models as a technique to "learn", but to to understand the actions of users and anticipate their behavior, so as to truly operate in symbiosis with them.
A Cognitive Framework for Delegation Between Error-Prone AI and Human Agents
With humans interacting with AI-based systems at an increasing rate, it is necessary to ensure the artificial systems are acting in a manner which reflects understanding of the human.
Structural invariants and semantic fingerprints in the "ego network" of words
In this respect, ring #1 can be seen as the semantic fingerprint of the ego network of words.
Predictive Auto-scaling with OpenStack Monasca
Cloud auto-scaling mechanisms are typically based on reactive automation rules that scale a cluster whenever some metric, e. g., the average CPU usage among instances, exceeds a predefined threshold.
Cellular traffic offloading via Opportunistic Networking with Reinforcement Learning
We show that our system based on Reinforcement Learning is able to automatically learn a very efficient strategy to reduce the traffic on the cellular network, without relying on any additional context information about the opportunistic network.
A communication efficient distributed learning framework for smart environments
In the specific case analysed in the paper, we focus on a learning task, considering two distributed learning algorithms.
Energy efficient distributed analytics at the edge of the network for IoT environments
We analyse the performance of different configurations of the distributed learning framework, in terms of (i) accuracy obtained in the learning task and (ii) energy spent to send data between the involved nodes.
Harnessing the Power of Ego Network Layers for Link Prediction in Online Social Networks
In order to validate this claim, we focus on popular feature-extraction prediction algorithms (both unsupervised and supervised) and we extend them to include social-circles awareness.
Optimising cost vs accuracy of decentralised analytics in fog computing environments
Decentralising AI tasks on several cooperative devices means identifying the optimal set of locations or Collection Points (CP for short) to use, in the continuum between full centralisation (i. e., all data on a single device) and full decentralisation (i. e., data on source locations).
Dynamic Hard Pruning of Neural Networks at the Edge of the Internet
Results show that DynHP compresses a NN up to $10$ times without significant performance drops (up to $3. 5\%$ additional error w. r. t.
