Demystifying Deep Learning in Networking

Zheng, Ying; Liu, Ziyu; You, Xinyu; Xu, Yuedong; Jiang, Junchen

doi:10.1145/3232565.3232569

Cited by 22 publications

(22 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some recent work focuses on the verification of DL-based networked systems [43] with advanced verification techniques [82], which is orthogonal to our work and could be adopted together for a more practical system. There are also some position papers that discuss the interpretability of DL-based networked systems [26,81], which, however, remain preliminary on both problems and solutions. In contrast, TranSys provides a systematic solution to effectively explain diverse DL-based networked systems with high quality for practical deployment, taking advantage of decision tree and hypergraph.…”

Section: Discussionmentioning

confidence: 99%

“…This could result in severe issues in system troubleshooting, lightweight deployment, and daily operation: (i) when DL-based networked systems make sub-optimal decisions, network operators have no clue on how to fix the problem; (ii) when systems are going to be deployed onto network devices, the resource consumption and decision latency are much worse than those of heuristics; and (iii) when operators want to perform additional manual operation actions (e.g., rerouting when congestion occurs), they have to retrain the learned model or test the actions in practice, which usually takes considerable time and expenses. The drawbacks above result in a general fear against DNNs for network operators [26,81] and prevent DNNs from deployment in the real world.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Interpreting Deep Learning-Based Networking Systems

Meng,

Wang,

Bai

et al. 2019

Preprint

View full text Add to dashboard Cite

While deep learning (DL)-based networked systems have shown great potential in various applications, a key drawback is that Deep Neural Networks (DNNs) in DL are blackboxes and nontransparent for network operators. The lack of interpretability makes DL-based networked systems challenging to operate and troubleshoot, which further prevents DL-based networked systems from deploying in practice. In this paper, we propose TranSys, a novel framework to explain DL-based networked systems for practical deployment. TranSys categorizes current DL-based networked systems and introduces different explanation methods based on decision tree and hypergraph to effectively explain DL-based networked systems. TranSys can explain the DNN policies in the form of decision trees and highlight critical components based on analysis over hypergraph. We evaluate Tran-Sys over several typical DL-based networked systems and demonstrate that TranSys can provide human-readable explanations for network operators. We also present three use cases of TranSys, which could (i) help network operators troubleshoot DL-based networked systems, (ii) improve the decision latency and resource consumption of DL-based networked systems by ∼10× on different metrics, and (iii) provide suggestions on daily operations for network operators when incidences occur.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Interpreting Deep Learning-Based Networking Systems

Meng,

Wang,

Bai

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…Using a network AI, [24], [25] and [26] focus on intelligent traffic routing for aggregated traffic characteristics and improved network analytics. For verification, prediction models can be cross-checked, e.g., with existing evaluations of the interpretability of deep learning models used in the area of computer networks [27]. An option is generative replay, whereby generated characteristic traffic is combined with prior data to ensure the adaptability of the prediction model [28].…”

Section: Related Workmentioning

confidence: 99%

Predicting Network Flow Characteristics Using Deep Learning and Real-World Network Traffic

Hardegen

Pfülb

Rieger

et al. 2020

IEEE Trans. Netw. Serv. Manage.

View full text Add to dashboard Cite

We present a processing pipeline for flow-based traffic classification using a machine learning component leveraging Deep Neural Networks (DNNs). The system is trained to predict likely characteristics of real-world traffic flows from a campus network ahead of time, e.g., a flow's throughput or duration. Training and evaluation of DNN models are continuously performed on a flow data stream collected from a university data center. Instead of the common binary classification into "mice" and "elephant" (throughput) or "short-term" and "long-term" (duration) flows, predicted flow characteristics are quantized into three classes. Various communication contexts (subset of network traffic, e.g., only TCP) and flow feature groups (subset of flow features, e.g., only a flow's 5-tuple), which are supported through an enrichment strategy, are considered and investigated. An in-depth description of the data acquisition process, including preprocessing steps and anonymization used to protect sensitive information, is given. Additionally, we employ an accelerated variant of t-distributed Stochastic Neighbor Embedding (t-SNE) to visualize network traffic data. This enables the understanding of traffic characteristics and relations between communication flows at a glance. Furthermore, possible use-cases and a highlevel architecture for flow-based routing scenarios utilizing the developed pipeline are proposed.

show abstract

“…These solutions, called Deep RL, have achieved remarkable results matching humans at playing Atari games [37], and beating the Go world champion [46]. These results have encouraged researchers to apply Deep RL to networking and systems problems, from routing, to congestion control, to video streaming, and to job scheduling [4,6,16,34,35,54,62,64,65]. Building a decision tree can be easily cast as an RL problem: the environment's state is the current decision tree, an action is either cutting a node or partitioning a set of rules, and the reward is either the classification time, memory footprint, or a combination of the two.…”

Section: How To Learn?mentioning

confidence: 99%

“…In particular, our approach learns to optimize packet classification for a given set of rules and objective, can easily incorporate pre-engineered heuristics to leverage their domain knowledge, and does so with little human involvement. The recent successes of deep learning in solving notoriously hard problems, such as image recognition [23] and language translation [51], have inspired many practitioners and researchers to apply deep learning, in particular, and machine learning, in general, to systems and networking problems [4,6,16,34,35,54,62,64,65]. While in some of these cases there are legitimate concerns about whether machine learning is the right solution for the problem at hand, we believe that deep learning is a good fit for our problem.…”

Section: Introductionmentioning

confidence: 99%

Neural packet classification

Liang

Zhu

Jin

et al. 2019

Proceedings of the ACM Special Interest Group on Data Communication

111

View full text Add to dashboard Cite

Packet classification is a fundamental problem in computer networking. This problem exposes a hard tradeoff between the computation and state complexity, which makes it particularly challenging. To navigate this tradeoff, existing solutions rely on complex hand-tuned heuristics, which are brittle and hard to optimize.In this paper, we propose a deep reinforcement learning (RL) approach to solve the packet classification problem. There are several characteristics that make this problem a good fit for Deep RL. First, many existing solutions iteratively build a decision tree by splitting nodes in the tree. Second, the effects of these actions (e.g., splitting nodes) can only be evaluated once the entire tree is built. These two characteristics are naturally captured by the ability of RL to take actions that have sparse and delayed rewards. Third, it is computationally efficient to generate data traces and evaluate decision trees, which alleviate the notoriously high sample complexity problem of Deep RL algorithms. Our solution, NeuroCuts, uses succinct representations to encode state and action space, and efficiently explore candidate decision trees to optimize for a global objective. It produces compact decision trees optimized for a specific set of rules and a given performance metric, such as classification time, memory footprint, or a combination of the two. Evaluation on ClassBench shows that NeuroCuts outperforms existing hand-crafted algorithms in classification time by 18% at the median, and reduces both classification time and memory footprint by up to 3×.

show abstract

Demystifying Deep Learning in Networking

Cited by 22 publications

References 9 publications

Interpreting Deep Learning-Based Networking Systems

Interpreting Deep Learning-Based Networking Systems

Predicting Network Flow Characteristics Using Deep Learning and Real-World Network Traffic

Neural packet classification

Contact Info

Product

Resources

About