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.
Paper proposes efficient weight updates for edge nodes with minimal communication.
Optimal client sampling reduces communication in federated learning.
Federated learning systems are vulnerable to attacks from malicious clients. As the central server in the system cannot govern the behaviors of the clients, a rogue client may initiate an attack by sending malicious model updates to the server, so as to degrade the learning performance or enforce targeted model poisoni…
Federated learning can be vulnerable to adversarial attacks, which this work addresses.
Federated learning is a distributed learning method to train a shared model by aggregating the locally-computed gradient updates. In federated learning, bandwidth and privacy are two main concerns of gradient updates transmission. This paper proposes an end-to-end encrypted neural network for gradient updates transmiss…
New method speeds up distributed linear regression.
Federated learning obtains a central model on the server by aggregating models trained locally on clients. As a result, federated learning does not require clients to upload their data to the server, thereby preserving the data privacy of the clients. One challenge in federated learning is to reduce the client-server c…
FedGLOMO accelerates FL convergence for non-convex functions.
This work provides bounds on generalization error and privacy leakage in federated learning.
Local adaptive methods in FL can accelerate convergence but introduce bias, which is corrected.
Detects backdoors in outsourced models by replicating training steps across multiple servers.
Federated learning is a method of training a global model from decentralized data distributed across client devices. Here, model parameters are computed locally by each client device and exchanged with a central server, which aggregates the local models for a global view, without requiring sharing of training data. The…
Federated learning is a distributed framework according to which a model is trained over a set of devices, while keeping data localized. This framework faces several systems-oriented challenges which include (i) communication bottleneck since a large number of devices upload their local updates to a parameter server, a…
Asynchronous distributed stochastic gradient descent methods have trouble converging because of stale gradients. A gradient update sent to a parameter server by a client is stale if the parameters used to calculate that gradient have since been updated on the server. Approaches have been proposed to circumvent this pro…
Byzantine-resilient federated learning with local iterations and robust mean estimation.
The increasing interest in user privacy is leading to new privacy preserving machine learning paradigms. In the Federated Learning paradigm, a master machine learning model is distributed to user clients, the clients use their locally stored data and model for both inference and calculating model updates. The model upd…
Paper tackles federated linear bandit learning with AirComp for noisy channels.
DFedAvgM is a decentralized FedAvg with momentum for privacy and communication efficiency.
We propose Zeno++, a new robust asynchronous Stochastic Gradient Descent~(SGD) procedure which tolerates Byzantine failures of the workers. In contrast to previous work, Zeno++ removes some unrealistic restrictions on worker-server communications, allowing for fully asynchronous updates from anonymous workers, arbitrar…
New method reduces FL communication cost by leveraging server's side information.
Synthetic data replaces model updates in federated learning.
CSE-FSL reduces communication and storage costs in federated learning.
Develops a new deep learning framework for privacy-preserving text representations.
Collaborative learning allows participants to jointly train a model without data sharing. To update the model parameters, the central server broadcasts model parameters to the clients, and the clients send updating directions such as gradients to the server. While data do not leave a client device, the communicated gra…
Distributed model training is vulnerable to byzantine system failures and adversarial compute nodes, i.e., nodes that use malicious updates to corrupt the global model stored at a parameter server (PS). To guarantee some form of robustness, recent work suggests using variants of the geometric median as an aggregation r…
Improved federated learning over-the-air reduces noise impact.
This work tackles resource allocation in asynchronous and stochastic systems.
This paper evaluates and compares gradient leakage attacks in federated learning.
New algorithm reduces FL sample and communication costs.
This paper proposes a cooperative mechanism for mitigating the performance degradation due to non-independent-and-identically-distributed (non-IID) data in collaborative machine learning (ML), namely federated learning (FL), which trains an ML model using the rich data and computational resources of mobile clients with…
Paper develops a federated learning method to protect privacy without sacrificing model utility.
AdaQuantFL reduces communication in federated learning by adaptively quantizing model updates.
Distributed optimization often consists of two updating phases: local optimization and inter-node communication. Conventional approaches require working nodes to communicate with the server every one or few iterations to guarantee convergence. In this paper, we establish a completely different conclusion that each node…
Improves asynchronous federated learning with queuing dynamics.
In federated learning, a central server coordinates the training of a single model on a massively distributed network of devices. This setting can be naturally extended to a multi-task learning framework, to handle real-world federated datasets that typically show strong statistical heterogeneity among devices. Despite…
A(DP)SGD improves federated learning privacy and efficiency.
FedLoRU improves FL efficiency by using low-rank updates.
We propose a real-time context-aware learning system along with the architecture that runs on the mobile devices, provide services to the user and manage the IoT devices. In this system, an application running on mobile devices collected data from the sensors, learned about the user-defined context, made predictions in…
New framework provides privacy guarantees for practical federated learning.
The current standalone deep learning framework tends to result in overfitting and low utility. This problem can be addressed by either a centralized framework that deploys a central server to train a global model on the joint data from all parties, or a distributed framework that leverages a parameter server to aggrega…
New insights into convergence and accuracy trade-offs in federated and meta-learning.
Tensor factorization models offer an effective approach to convert massive electronic health records into meaningful clinical concepts (phenotypes) for data analysis. These models need a large amount of diverse samples to avoid population bias. An open challenge is how to derive phenotypes jointly across multiple hospi…
Federated CTMC model estimates bridge deterioration hazards without sharing raw data.
We study distributed stochastic convex optimization under the delayed gradient model where the server nodes perform parameter updates, while the worker nodes compute stochastic gradients. We discuss, analyze, and experiment with a setup motivated by the behavior of real-world distributed computation networks, where the…
Distributed training of deep nets is an important technique to address some of the present day computing challenges like memory consumption and computational demands. Classical distributed approaches, synchronous or asynchronous, are based on the parameter server architecture, i.e., worker nodes compute gradients which…
Study protects federated learning models from eavesdropping attacks.
Secure federated learning framework resists adversarial users.
Study on incentivizing truthfulness in federated learning with heterogeneous data.