Category
1,771 papers
Federated learning, as a privacy-preserving distributed machine learning paradigm, faces significant threats from backdoor attacks. Compared to centralized attacks, distributed backdoor attacks are more harmful but require more poisoned samples to compensate for the loss of trigger strength due to decomposition. Fixed...
A constrained Bayesian Optimization framework for the efficient configuration of HFL deployments that captures user-defined trade-offs among energy consumption, execution time, and predictive performance, while explicit constraints ensure compliance with deployment-specific resource and accuracy requirements.
One-shot federated graph learning generally aims to train Graph Neural Networks (GNNs) across clients with disconnected subgraphs in a single communication round. Existing methods predominantly design advanced optimization strategies under the premise that local GNN training is indispensable. However, empirical observa...
CALM is proposed, which replaces every hard decision with a smooth trust gate at three levels: per class, teachers are weighted by agreement with the peer consensus; per sample, distillation is scaled by the teachers'divergence from that target; and a label gate scales it by how strongly the target supports the sample'...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Privacy-sensitive surveillance systems could benefit from large vision-language models (VLMs), but such models typically require centralized access to raw video. In federated learning settings, this challenge is amplified by non-independent and identically distributed (non-IID) client data, which can make direct multic...
FedSubMuon is proposed, a communication-efficient federated Muon fine-tuning method that optimizes compact coefficient matrices within shared structured subspaces that keeps Muon on a single matrix-valued trainable object, while reducing the client upload to compact coefficient matrices.
This article proposes and analyses a conceptual, policy-governed federated architecture derived from the architectural work of the Horizon Europe NOUS project and maps architectural functions onto major European reference initiatives.
A privacy-preserving dynamic evaluation system for cross-platform social media marketing effectiveness based on federated learning that improves the accuracy, interpretability, and privacy protection of cross-platform marketing evaluation.
This study presents a PRISMA-guided systematic review integrating agentic decision theory with organizational information systems perspectives, including the Technology Acceptance Model, Task-Technology Fit, and Sociotechnical Systems Theory.
This survey reviews the intersection of deep learning and big data along three axes: the neural architectures used to model large-scale data, the distributed computing frameworks that make training such models tractable, and the persistent challenges of scalability, data quality, privacy, andinterpretability that const...
The Federated Learning-based Silver Economy Prediction Framework (FL-SEPF), which is a collaborative framework for privacy-preserving prediction in the silver economy, features a four-layer architecture with an adaptive weighted federated aggregation strategy that dynamically computes platform-specific weights based on...
Comparative benchmarking proves that ADEFIF surpasses all current frameworks such as Traditional Digital Forensics, Multidimensional AI Forensic Analysis Framework (MAFAF), and Privacy-by-Design AI Forensic Model (PbDAIF), in all the assessment dimensions.
StudentSim is a research system for evaluating and improving AI tutoring tools before they are tested with learners. It models how individuals may engage with tutors, giving feedback to improve tutor performance across subjects like chess, writing, and mathematics. The post Simulating student learning for better AI tutoring appeared first on Microsoft Research.
Students in MIT’s Concourse program delve deeply into the human condition, debate challenging questions, and learn to develop judgment about issues that can’t be quantified.
Training AI agents with reinforcement learning can be challenging because their tools, context, and decision-making are managed by complex frameworks. Agent Lightning connects existing agents to RL training, making it easier to improve them without rebuilding them. The post Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses appeared first on Microsoft Research.
The effort aims to help U.S. learners from kindergarten to community college, with an emphasis on math, making, and the constructive use of AI.
Associate Professor Cathy Wu uses reinforcement learning to help map out improvements to transportation and other multifaceted systems.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
