This paper analyzes user-level local differential privacy in distributed systems.
problem The relationship between user-level and item-level local differential privacy under the local model is complex.
method The paper analyzes the mean estimation problem and applies it to stochastic optimization, classification, and regression. It proposes adaptive strategies to achieve optimal performance at all privacy levels.
result The proposed methods are minimax optimal up to logarithmic factors and show that user-level DP can lead to faster convergence rates than item-level DP.
A new algorithm estimates mean under varying user data sizes with local differential privacy.
problem Mean estimation with user-level local differential privacy under varying data sizes.
method Distribution-aware mean estimation algorithm for users with varying data sizes.
result Upper and lower bounds on the worst-case risk for mean estimation are derived.
Optimizes convergence time of federated learning over wireless networks.
problem Limited resource blocks in wireless networks affect federated learning convergence time and performance.
method Formulates an optimization problem to minimize convergence time while optimizing performance, proposes a probabilistic user selection scheme and uses ANNs for estimation.
result Improves convergence time and performance of federated learning over wireless networks.
FURL improves model accuracy in FL by locally training user embeddings.
problem Improving prediction accuracy of neural-network-based models in Federated Learning.
method FURL divides model parameters into federated and private parameters, training private parameters locally.
result Significant performance improvement with 8% and 51% increases on two datasets.
Improved locally private sparse estimation with multiple samples per user.
problem Challenges in high-dimensional locally private sparse estimation.
method Proposes a framework for user-level locally private sparse linear regression with multiple samples per user.
result Eliminates the dependency of dimensionality on error bounds, achieving tighter error bounds.
Locally private Gaussian estimation tackles privacy in i.i.d. sample mean estimation.
problem Estimating the mean of an unknown Gaussian distribution while maintaining local differential privacy for each user.
method Adaptive two-round and nonadaptive one-round solutions for locally private Gaussian estimation.
result Upper bounds partially match with information-theoretic lower bounds, showing tightness up to logarithmic factors.
Secure federated learning framework resists adversarial users.
problem Resilience against adversarial (Byzantine) users in federated learning.
method Integrated stochastic quantization, verifiable outlier detection, and secure model aggregation.
result First single-server Byzantine-resilient secure aggregation framework (BREA) for secure federated learning.
P2B improves local agent performance with differential privacy.
problem Improving local agent performance with differential privacy.
method Differential privacy technique to collect and update local agents' feedback.
result Competitive performance on synthetic and real-world data.
Paper addresses robust sparse vector mean estimation under local differential privacy.
problem Challenges in defending poisoning attacks on multi-item users in LDP protocols.
method Randomized Projection with Clipping (RPC) to handle clipping bias and enhance robustness.
result Proposes a method that achieves comparable or better performance than existing methods under trusted environments and significantly enhances robustness under untrusted environments.
Study assesses human interpretability of machine learning models.
problem Ensuring machine learning models are understandable by humans.
method User study with 1,000 participants testing simulatability and 'what if' local explainability.
result Increased runtime operation count correlates with decreased human accuracy on local interpretability tasks.
A fuzzy recommender system using PageRank for community detection.
problem Improving recommendation systems for large user communities.
method Fuzzy community detection using personalized PageRank.
result The method outperforms recent recommender systems on MovieLens and FilmTrust datasets.
Paper presents a simple method for accurate user localization in urban areas.
problem Poor GPS performance in dense urban environments.
method Localization based on pathloss using base station signal strengths and RadioUNet approximations.
result Accurate user location extraction in urban environments.
Local GD proves effective for heterogeneous data in federated learning.
problem Minimizing functions from private, heterogeneous data in federated learning.
method Local gradient descent for smooth, convex functions.
result Communication complexity similar to gradient descent in low accuracy regime.
Paper proposes a transfer learning approach for decentralized QoE estimation.
problem Challenges in QoE model development due to small datasets, user diversity, and IPR/privacy concerns.
method A transfer learning-based ML model training approach that allows decentralized local models to share generic indicators and customize them further.
result The approach shows advantages of stacking various generic and specific models with corresponding weight factors.
While a user's preference is directly reflected in the interactive choice process between her and the recommender, this wealth of information was not fully exploited for learning recommender models. In particular, existing collaborative filtering (CF) approaches take into account only the binary events of user actions …
Paper proposes a privacy-preserving DML framework using local randomization and ADMM perturbation.
problem Privacy concerns in distributed machine learning with sensitive user data.
method Local randomization and ADMM perturbation to provide differential privacy and heterogeneous privacy levels.
result The framework minimizes privacy losses and maintains model generalization.
CC charts radio geometry for user localization.
problem Locating users in radio environments.
method Unsupervised learning from passive CSI.
result Extracts channel features for spatial comparison.
Paper proposes incentives for federated learning to ensure truthful contributions.
problem Ensuring truthful contributions from decentralized users in federated learning.
method Introduces a scoring rule based framework to incentivize truthful reporting of local hypotheses at a Bayesian Nash Equilibrium.
result Proposed solution verified using MNIST and CIFAR-10 datasets, showing decreasing scores for low-quality hypotheses.
FedBE aggregates local models into a robust global model via Bayesian inference.
problem Challenges in aggregating non-i.i.d. local models into a global model in federated learning.
method FedBE uses Bayesian inference to sample and combine higher-quality global models from local models.
result FedBE leads to more robust aggregation of local models into a global model, especially when data is non-i.i.d.
WassFFed addresses fairness in Federated Learning by ensuring consistency between local and global models.
problem Achieving fairness in Federated Learning where data is distributed among diverse user groups.
method WassFFed employs a Wasserstein barycenter calculation to aggregate local models' outputs, ensuring consistency and fairness.
result WassFFed outperforms existing approaches in balancing accuracy and fairness.
Memory-Augmented Meta-Optimization improves cold-start recommendation.
problem Cold-start problem in recommender systems for new users or items.
method Memory-Augmented Meta-Optimization approach with personalized and task-specific memories.
result Significant improvement in cold-start recommendation performance on multiple datasets.
Federated learning uses worst-case optimization to handle uncertain local data impacts.
problem Handling uncertainty in local data sets in federated learning.
method Reformulate FL problem using worst-case optimization theory, considering local data as uncertain functions bounded in a closed region.
result Comparison of FL performance with centralized learning and application of regularization factors.
Decor protects decentralized learning models from curious users.
problem Privacy violation in decentralized learning.
method Decor uses correlated Gaussian noises to protect local models in decentralized SGD with differential privacy guarantees.
result Decor matches central DP optimal privacy-utility trade-off for arbitrary connected graphs.
HCRNN uses hierarchical contexts to improve recommendation models.
problem Challenges in modeling user interest transitions and drifts in recommendation systems.
method Introduces HCRNN with three hierarchical contexts (global, local, temporary) and a hierarchical context-based gate structure.
result HCRNN outperformed other models in sequential recommendation tasks.
New algorithm reduces privacy cost of LDP to central privacy model.
problem Collecting sensitive statistics from multiple users over time.
method Privacy amplification technique using permutation-invariant algorithms.
result Privacy cost of LDP can be much lower in central model.
New strategies reduce FL's impact on client resources, enabling larger models and more users.
problem Communication bottleneck in Federated Learning on heterogeneous edge networks.
method Lossy compression and Federated Dropout to reduce client-to-server communication and local computation.
result Up to 14x reduction in server-to-client communication, 1.7x reduction in local computation, and 28x reduction in upload communication.
Federated CTMC model estimates bridge deterioration hazards without sharing raw data.
problem Bridge inspection data privacy and cross-organizational data sharing constraints.
method Federated CTMC hazard model with local optimization and FedAvg aggregation.
result Federated model converges on global benchmark parameters without data transfer.
PriRec preserves privacy in POI recommendation by keeping data and models on users' devices.
problem Privacy concerns in centralized POI recommendation models.
method Local differential privacy for sensitive data, secure decentralized gradient descent for linear models, secure aggregation for feature interactions.
result PriRec achieves comparable or better recommendation accuracy than FM while protecting user privacy.
FAIRY explains user actions and social media feeds.
problem Users struggle to understand why certain items appear in their social feeds.
method FAIRY uses an interaction graph to model user behavior and ranks feed items, scoring paths connecting user actions and feed items.
result FAIRY provides clear explanations for user actions and feed items, enhancing transparency and user understanding.
Paper addresses FL over wireless networks, optimizing learning and resource allocation.
problem Training FL algorithms over wireless networks with limited resources and errors.
method Formulated as an optimization problem to minimize FL loss function, derived expected convergence rate, derived optimal transmit power, optimized user selection and RB allocation.
result Joint framework reduces FL loss by up to 10% and 16% compared to alternatives.
Detects anomalous behavior in social media users by analyzing content and connections.
problem Identifying disruptive patterns in user behavior on social media platforms.
method Joint representation learning of content and connection to detect anomalous behavior.
result Observed densely connected users engaging in local politics and exhibiting troll-like behavior.
Combining global and local explanations improves user understanding of RL agents.
problem Challenges in explaining agent behavior due to large state spaces and delayed rewards.
method Integrating strategy summaries with saliency maps to provide both global and local explanations.
result Summaries including important states significantly improve user understanding of RL agents.
Paper tackles energy efficiency in FL over wireless networks.
problem Energy efficient transmission and computation resource allocation for FL over wireless networks.
method Formulated as an optimization problem, iterative algorithm derived with closed-form solutions for time, bandwidth, power, and accuracy.
result Proposed algorithms reduce up to 59.5% energy consumption compared to conventional FL methods.
Paper improves privacy-accuracy balance in federated learning.
problem Privacy-accuracy tradeoffs in federated learning.
method Personalized federated learning with joint differential privacy.
result Coordination of local and centralized learning improves accuracy while maintaining privacy.
This work improves privacy in the shuffle model for summing real numbers.
problem Improving privacy in the shuffle model for data aggregation.
method Developed optimal single message protocol and new lower and upper bounds for privacy amplification.
result Improved accuracy and communication in summing real numbers protocol.
New methods protect privacy while providing accurate prediction sets.
problem Privacy-preserving conformal prediction for untrusted aggregators.
method Two LDP approaches: k-ary randomized response and binary search response.
result Finite-sample coverage guarantees and robust coverage under randomization.
A DRL approach optimizes computation offloading in MEC systems for mobile users.
problem Optimizing computation offloading in MEC systems with mobile users and stochastic task arrivals.
method Deep Deterministic Policy Gradient (DDPG) for decentralized dynamic computation offloading.
result The DDPG-based strategy outperforms conventional strategies in terms of computation cost and power-delay tradeoff.
Paper studies user-level differential privacy in federated linear contextual bandits.
problem Federated learning with user-level differential privacy constraints.
method Unified federated bandits framework, CDP and LDP definitions, ROBIN algorithm.
result Near-optimal learning under user-level CDP with privacy budget and number of clients.
Unified neural framework for multi-relational recommender systems.
problem Accurately capturing users' fine-grained preferences from diverse feedback types.
method Multi-Relational Memory Network (MRMN) framework that models fine-grained user-item relations and discriminates between feedback types.
result The proposed MRMN model outperforms state-of-the-art algorithms in various recommender scenarios.
Podcast recommendations improved by analyzing user listening paths.
problem Challenges in recommending podcasts effectively.
method Analyzes user listening paths as sequential trajectories for recommendations.
result 450% increase in effectiveness over baseline.
Federated approach protects privacy while learning user patterns.
problem Protecting sensitive data in recommendation systems.
method Differentially private prototypes for global and local models.
result Local adaptation improves recommendation accuracy and relevance.
Federated Collaborative Filtering preserves user privacy in recommendation systems.
problem Preserving user privacy in machine learning models.
method Federated Learning approach with stochastic gradient updates.
result Collaborative filtering can be successfully federated without accuracy loss.
The paper addresses privacy-preserving BAI in clinical trials and user studies.
problem Privacy-preserving Best Arm Identification in adaptive clinical trials and user studies.
method The paper derives lower bounds on sample complexity for BAI algorithms with differential privacy constraints and proposes private variants of Top Two algorithms.
result Private variants of Top Two algorithms achieve asymptotic optimality in terms of sample complexity for BAI problems under differential privacy constraints.
FLAME improves privacy in federated learning without trusted parties.
problem Ensuring privacy in federated learning without trusted parties.
method FLAME uses the shuffle model of differential privacy to achieve better accuracy and privacy.
result FLAME protocols improve testing accuracy by 60.7% compared to local model FL.
Develops privacy-preserving methods for longitudinal linear regression.
problem Protecting individual information in longitudinal data with privacy-preserving statistics.
method Proposes a user-level private regression estimator and a privatized covariance estimator for longitudinal linear regression under user-level differential privacy.
result Establishes theoretical guarantees for practical user-level differential privacy estimation and inference in longitudinal linear regression.
Improved federated learning over-the-air reduces noise impact.
problem Noise in OTA FL degrades model accuracy.
method Developed COTAF algorithm with precoding and scaling.
result COTAF achieves similar convergence rate to error-free channels.
New bounds for LDP with heterogeneous privacy levels guaranteeing high probability of accuracy.
problem Statistical estimation under LDP with users having varying privacy levels.
method Developed finite sample upper bounds in ℓ_2-norm with high probability, complemented by lower bounds.
result Optimal guarantees for heterogeneous LDP in terms of probability and constants.
A new method for multi-criteria recommender systems using graph attention networks.
problem Lack of nuanced relationships between users and items based on specific criteria.
method MDGAT, a multi-edge bipartite graph with dual attention networks and contrastive learning.
result MDGAT achieves higher accuracy in predicting item ratings compared to baseline methods.