arXiv subjects

Muntasir Raihan Rahman

Publications and source records attributed to Muntasir Raihan Rahman.

5 recordsLinked to original sources

arXiv2020

Privacy-preserving Decentralized Aggregation for Federated Learning

Federated learning is a promising framework for learning over decentralized data spanning multiple regions. This approach avoids expensive central training data aggregation cost and can improve privacy because distributed sites do not have to reveal privacy-sensitive data. In this paper, we develop a privacy-preserving decentralized aggregation protocol for federated learning. We formulate the distributed aggregation protocol with the Alternating Direction Method of Multiplier (ADMM) and examine its privacy weakness. Unlike prior work that use Differential Privacy or homomorphic encryption for privacy, we develop a protocol that controls communication among participants in each round of aggregation to minimize privacy leakage. We establish its privacy guarantee against an honest-but-curious adversary. We also propose an efficient algorithm to construct such a communication pattern, inspired by combinatorial block design theory. Our secure aggregation protocol based on this novel group communication pattern design leads to an efficient algorithm for federated training with privacy guarantees. We evaluate our federated training algorithm on image classification and next-word prediction applications over benchmark datasets with 9 and 15 distributed sites. Evaluation results show that our algorithm performs comparably to the standard centralized federated learning method while preserving privacy; the degradation in test accuracy is only up to 0.73%.

cs.LG↗

arXiv2019

Deep Reinforcement Learning for Network Slicing with Heterogeneous Resource Requirements and Time Varying Traffic Dynamics

Efficient network slicing is vital to deal with the highly variable and dynamic characteristics of network traffic generated by a varied range of applications. The problem is made more challenging with the advent of new technologies such as 5G and new architectures such as SDN and NFV. Network slicing addresses a challenging dynamic network resource allocation problem where a single network infrastructure is divided into (virtual) multiple slices to meet the demands of different users with varying requirements, the main challenges being --- the traffic arrival characteristics and the job resource requirements (e.g., compute, memory and bandwidth resources) for each slice can be highly dynamic. Traditional model-based optimization or queueing theoretic modeling becomes intractable with the high reliability, and stringent bandwidth and latency requirements imposed by 5G technologies. In addition these approaches lack adaptivity in dynamic environments. We propose a deep reinforcement learning approach to address this dynamic coupled resource allocation problem. Model evaluation using both synthetic simulation data and real workload driven traces demonstrates that our deep reinforcement learning solution improves overall resource utilization, latency performance, and demands satisfied as compared to a baseline equal-slicing strategy.

cs.NI↗

arXiv2017

Inferring Formal Properties of Production Key-Value Stores

Production distributed systems are challenging to formally verify, in particular when they are based on distributed protocols that are not rigorously described or fully understood. In this paper, we derive models and properties for two core distributed protocols used in eventually consistent production key-value stores such as Riak and Cassandra. We propose a novel modeling called certified program models, where complete distributed systems are captured as programs written in traditional systems languages such as concurrent C. Specifically, we model the read-repair and hinted-handoff recovery protocols as concurrent C programs, test them for conformance with real systems, and then verify that they guarantee eventual consistency, modeling precisely the specification as well as the failure assumptions under which the results hold.

cs.DC↗

arXiv2016

Characterizing and Adapting the Consistency-Latency Tradeoff in Distributed Key-value Stores

The CAP theorem is a fundamental result that applies to distributed storage systems. In this paper, we first present and prove two CAP-like impossibility theorems. To state these theorems, we present probabilistic models to characterize the three important elements of the CAP theorem: consistency (C), availability or latency (A), and partition tolerance (P). The theorems show the un-achievable envelope, i.e., which combinations of the parameters of the three models make them impossible to achieve together. Next, we present the design of a class of systems called PCAP that perform close to the envelope described by our theorems. In addition, these systems allow applications running on a single data-center to specify either a latency SLA or a consistency SLA. The PCAP systems automatically adapt, in real-time and under changing network conditions, to meet the SLA while optimizing the other C/A metric. We incorporate PCAP into two popular key-value stores -- Apache Cassandra and Riak. Our experiments with these two deployments, under realistic workloads, reveal that the PCAP system satisfactorily meets SLAs, and performs close to the achievable envelope. We also extend PCAP from a single data-center to multiple geo-distributed data-centers.

cs.DC↗

arXiv2012

Toward a Principled Framework for Benchmarking Consistency

Large-scale key-value storage systems sacrifice consistency in the interest of dependability (i.e., partition tolerance and availability), as well as performance (i.e., latency). Such systems provide eventual consistency,which---to this point---has been difficult to quantify in real systems. Given the many implementations and deployments of eventually-consistent systems (e.g., NoSQL systems), attempts have been made to measure this consistency empirically, but they suffer from important drawbacks. For example, state-of-the art consistency benchmarks exercise the system only in restricted ways and disrupt the workload, which limits their accuracy. In this paper, we take the position that a consistency benchmark should paint a comprehensive picture of the relationship between the storage system under consideration, the workload, the pattern of failures, and the consistency observed by clients. To illustrate our point, we first survey prior efforts to quantify eventual consistency. We then present a benchmarking technique that overcomes the shortcomings of existing techniques to measure the consistency observed by clients as they execute the workload under consideration. This method is versatile and minimally disruptive to the system under test. As a proof of concept, we demonstrate this tool on Cassandra.

cs.DC↗