On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

12 results for “Cross-Device”

DoCoFL: Downlink Compression for Cross-Device Federated Learningcs.LG

DoCoFL compresses model updates for cross-device federated learning.

problem Downlink compression for cross-device federated learning where clients may appear only once.

method Proposes DoCoFL framework for downlink compression in cross-device federated learning.

result Significant bi-directional bandwidth reduction with competitive accuracy.

Federated Learning Downlink Compression Cross-Device Bi-Directional Heterogeneous Clients

2023-02-01abs ↗pdf ↗

Unsupervised Cross-domain Image Classification by Distance Metric Guided Feature Alignmentcs.LG

MetFA aligns source and target domains for cross-device image classification.

problem Learning discriminative class boundaries across different domains.

method Distance metric guided feature alignment (MetFA) for domain-invariant and discriminative feature extraction.

result MetFA outperforms state-of-the-art methods in cross-device image classification.

unsupervised domain adaptation cross-device image classification deep neural networks domain shift feature alignment

2020-08-19abs ↗pdf ↗

Pursuing Overall Welfare in Federated Learning through Sequential Decision Makingcs.LG

AAggFF improves federated learning fairness through sequential decision making.

problem Achieving client-level fairness in federated learning systems.

method Unified online convex optimization framework for adaptive aggregation strategies.

result AAggFF achieves better client-level fairness in federated learning.

federated learning sequential decision making fairness aggregation regret bound

2024-05-31abs ↗pdf ↗

Cross Device Matching for Online Advertising with Neural Feature Ensembles : First Place Solution at CIKM Cup 2016cs.LG

We describe the 1st place winning approach for the CIKM Cup 2016 Challenge. In this paper, we provide an approach to reasonably identify same users across multiple devices based on browsing logs. Our approach regards a candidate ranking problem as pairwise classification and utilizes an unsupervised neural feature ense…

2016-10-23abs ↗pdf ↗

Unbounded Gradients in Federated Learning with Buffered Asynchronous Aggregationcs.LG

FedBuff improves federated learning scalability with asynchronous updates.

problem Limited scalability of federated learning with synchronous updates.

method Introduces asynchronous updates (staleness) in federated learning.

result Theoretical analysis shows improved convergence rate with boundedness removed.

federated learning asynchronous updates scalability convergence rate secure aggregation

2022-10-03abs ↗pdf ↗

FLAIR: Federated Learning Annotated Image Repositorycs.LG

FLAIR dataset for federated learning benchmarks.

problem Lack of suitable federated learning datasets.

method Curated large-scale annotated image dataset for multi-label classification.

result FLAIR captures real-world federated learning challenges.

federated learning image dataset benchmark multi-label classification heterogeneous data

2022-07-18abs ↗pdf ↗

Mime: Mimicking Centralized Stochastic Algorithms in Federated Learningcs.LG

Mime algorithm improves federated learning by adapting centralized methods.

problem Mitigating client drift in federated learning.

method Combines control variates and server-level statistics to adapt centralized algorithms to federated learning.

result Mime outperforms any centralized method in federated learning.

federated learning client drift control variates momentum variance reduction

2020-08-08abs ↗pdf ↗

FedPop: A Bayesian Approach for Personalised Federated Learningcs.LG

Proposes FedPop for personalised federated learning with uncertainty quantification.

problem Uncertainty quantification and client drift in personalised federated learning.

method FedPop recasts FL into population modeling with Markov chain Monte Carlo methods.

result Non-asymptotic convergence guarantees for uncertainty quantification.

federated learning personalized uncertainty quantification Markov chain Monte Carlo client drift

2022-06-07abs ↗pdf ↗

On Privacy and Personalization in Cross-Silo Federated Learningcs.LG

Study improves privacy in cross-silo federated learning by personalizing data.

problem Privacy concerns in cross-silo federated learning.

method Introduced sample-level differential privacy for silos, analyzed mean-regularized multi-task learning.

result Mean-regularized multi-task learning is a strong baseline for cross-silo federated learning under stronger privacy requirements.

differential privacy federated learning cross-silo personalization privacy regulations

2022-06-16abs ↗pdf ↗

FedShuffle: Recipes for Better Use of Local Work in Federated Learningcs.LG

FedShuffle improves local updates in FL, especially with data imbalance.

problem Data imbalance in FL leads to different clients performing different numbers of local updates.

method FedShuffle incorporates random reshuffling, data imbalance, and client sampling.

result FedShuffle improves upon FL methods that assume homogeneous updates in heterogeneous setups.

Federated Learning Local Updates Data Imbalance Random Reshuffling Client Sampling

2022-04-27abs ↗pdf ↗

Self-organizing Democratized Learning: Towards Large-scale Distributed Learning Systemscs.LG

New approach for large-scale distributed learning systems that improve generalization performance.

problem Transitioning from centralized to distributed AI systems for complex learning tasks.

method Self-organizing hierarchical structuring mechanism based on agglomerative clustering, hierarchical generalization, and personalized learning.

result Demonstrates better generalization performance compared to conventional federated learning algorithms.

distributed learning democratized learning self-organization federated learning generalization

2020-07-07abs ↗pdf ↗

Distributed and Democratized Learning: Philosophy and Research Challengescs.AI

Paper proposes a new AI design philosophy for distributed learning.

problem Designing AI systems that mimic human cognitive capabilities.

method Democratized learning (Dem-AI) with self-organized hierarchical agents.

result Self-organized learning systems can perform complex tasks more efficiently.

Democratized Learning Artificial General Intelligence Hierarchical Agents Self-Organization Plasticity-Stability Transition

2020-03-18abs ↗pdf ↗