arXiv subjects

Yongquan Fu

Publications and source records attributed to Yongquan Fu.

7 recordsLinked to original sources

arXiv2024

RiskQ: Risk-sensitive Multi-Agent Reinforcement Learning Value Factorization

Multi-agent systems are characterized by environmental uncertainty, varying policies of agents, and partial observability, which result in significant risks. In the context of Multi-Agent Reinforcement Learning (MARL), learning coordinated and decentralized policies that are sensitive to risk is challenging. To formulate the coordination requirements in risk-sensitive MARL, we introduce the Risk-sensitive Individual-Global-Max (RIGM) principle as a generalization of the Individual-Global-Max (IGM) and Distributional IGM (DIGM) principles. This principle requires that the collection of risk-sensitive action selections of each agent should be equivalent to the risk-sensitive action selection of the central policy. Current MARL value factorization methods do not satisfy the RIGM principle for common risk metrics such as the Value at Risk (VaR) metric or distorted risk measurements. Therefore, we propose RiskQ to address this limitation, which models the joint return distribution by modeling quantiles of it as weighted quantile mixtures of per-agent return distribution utilities. RiskQ satisfies the RIGM principle for the VaR and distorted risk metrics. We show that RiskQ can obtain promising performance through extensive experiments. The source code of RiskQ is available in https://github.com/xmu-rl-3dv/RiskQ.

cs.MA↗

arXiv2023

Comprehensive Deadlock Prevention for GPU Collective Communication

Distributed deep neural network training necessitates efficient GPU collective communications, which are inherently susceptible to deadlocks. GPU collective deadlocks arise easily in distributed deep learning applications when multiple collectives circularly wait for each other. GPU collective deadlocks pose a significant challenge to the correct functioning and efficiency of distributed deep learning, and no general effective solutions are currently available. Only in specific scenarios, ad-hoc methods, making an application invoke collectives in a consistent order across GPUs, can be used to prevent circular collective dependency and deadlocks. This paper presents DFCCL, a novel GPU collective communication library that provides a comprehensive approach for GPU collective deadlock prevention while maintaining high performance. DFCCL achieves preemption for GPU collectives at the bottom library level, effectively preventing deadlocks even if applications cause circular collective dependency. DFCCL ensures high performance with its execution and scheduling methods for collectives. Experiments show that DFCCL effectively prevents GPU collective deadlocks in various situations. Moreover, extensive evaluations demonstrate that DFCCL delivers performance comparable to or superior to NCCL, the state-of-the-art collective communication library highly optimized for NVIDIA GPUs.

cs.DC↗

arXiv2021

S2 Reducer: High-Performance Sparse Communication to Accelerate Distributed Deep Learning

Distributed stochastic gradient descent (SGD) approach has been widely used in large-scale deep learning, and the gradient collective method is vital to ensure the training scalability of the distributed deep learning system. Collective communication such as AllReduce has been widely adopted for the distributed SGD process to reduce the communication time. However, AllReduce incurs large bandwidth resources while most gradients are sparse in many cases since many gradient values are zeros and should be efficiently compressed for bandwidth saving. To reduce the sparse gradient communication overhead, we propose Sparse-Sketch Reducer (S2 Reducer), a novel sketch-based sparse gradient aggregation method with convergence guarantees. S2 Reducer reduces the communication cost by only compressing the non-zero gradients with count-sketch and bitmap, and enables the efficient AllReduce operators for parallel SGD training. We perform extensive evaluation against four state-of-the-art methods over five training models. Our results show that S2 Reducer converges to the same accuracy, reduces 81\% sparse communication overhead, and achieves 1.8$ \times $ speedup compared to state-of-the-art approaches.

cs.DC↗

arXiv2021

CGNN: Traffic Classification with Graph Neural Network

Traffic classification associates packet streams with known application labels, which is vital for network security and network management. With the rise of NAT, port dynamics, and encrypted traffic, it is increasingly challenging to obtain unified traffic features for accurate classification. Many state-of-the-art traffic classifiers automatically extract features from the packet stream based on deep learning models such as convolution networks. Unfortunately, the compositional and causal relationships between packets are not well extracted in these deep learning models, which affects both prediction accuracy and generalization on different traffic types. In this paper, we present a chained graph model on the packet stream to keep the chained compositional sequence. Next, we propose CGNN, a graph neural network based traffic classification method, which builds a graph classifier over automatically extracted features over the chained graph. Extensive evaluation over real-world traffic data sets, including normal, encrypted and malicious labels, show that, CGNN improves the prediction accuracy by 23\% to 29\% for application classification, by 2\% to 37\% for malicious traffic classification, and reaches the same accuracy level for encrypted traffic classification. CGNN is quite robust in terms of the recall and precision metrics. We have extensively evaluated the parameter sensitivity of CGNN, which yields optimized parameters that are quite effective for traffic classification.

cs.LG↗

arXiv2020

Nyström Approximation with Nonnegative Matrix Factorization

Motivated by the needs of estimating the proximity clustering with partial distance measurements from vantage points or landmarks for remote networked systems, we show that the proximity clustering problem can be effectively formulated as the Nyström approximation problem, which solves the kernel K-means clustering problem in the complex space. We implement the Nyström approximation based on a landmark based Nonnegative Matrix Factorization (NMF) process. Evaluation results show that the proposed method finds nearly optimal clustering quality on both synthetic and real-world data sets as we vary the range of parameter choices and network conditions.

cs.LG↗

arXiv2019

Locality-Sensitive Sketching for Resilient Network Flow Monitoring

Network monitoring is vital in modern clouds and data center networks for traffic engineering, network diagnosis, network intrusion detection, which need diverse traffic statistics ranging from flow size distributions to heavy hitters. To cope with increasing network rates and massive traffic volumes, sketch based approximate measurement has been extensively studied to trade the accuracy for memory and computation cost, which unfortunately, is sensitive to hash collisions. In addition, deploying the sketch involves fine-grained performance control and instrumentation. This paper presents a locality-sensitive sketch (LSS) to be resilient to hash collisions. LSS proactively minimizes the estimation error due to hash collisions with an autoencoder based optimization model, and reduces the estimation variance by keeping similar network flows to the same bucket array. To illustrate the feasibility of the sketch, we develop a disaggregated monitoring application that supports non-intrusive sketching deployment and native network-wide analysis. Testbed shows that the framework adapts to line rates and provides accurate query results. Real-world trace-driven simulations show that LSS remains stable performance under wide ranges of parameters and dramatically outperforms state-of-the-art sketching structures, with over $10^3$ to $10^5$ times reduction in relative errors for per-flow queries as the ratio of the number of buckets to the number of network flows reduces from 10\% to 0.1\%.

cs.NI↗

arXiv2011

HybridNN: Supporting Network Location Service on Generalized Delay Metrics

Distributed Nearest Neighbor Search (DNNS) locates service nodes that have shortest interactive delay towards requesting hosts. DNNS provides an important service for large-scale latency sensitive networked applications, such as VoIP, online network games, or interactive network services on the cloud. Existing work assumes the delay to be symmetric, which does not generalize to applications that are sensitive to one-way delays, such as the multimedia video delivery from the servers to the hosts. We propose a relaxed inframetric model for the network delay space that does not assume the triangle inequality and delay symmetry to hold. We prove that the DNNS requests can be completed efficiently if the delay space exhibits modest inframetric dimensions, which we can observe empirically. Finally, we propose a DNNS method named HybridNN (\textit{Hybrid} \textit{N}earest \textit{N}eighbor search) based on the inframetric model for fast and accurate DNNS. For DNNS requests, HybridNN chooses closest neighbors accurately via the inframetric modelling, and scalably by combining delay predictions with direct probes to a pruned set of neighbors. Simulation results show that HybridNN locates nearly optimally the nearest neighbor. Experiments on PlanetLab show that HybridNN can provide accurate nearest neighbors that are close to optimal with modest query overhead and maintenance traffic.

cs.DC↗