@inproceedings{50807, author = {{Hu, Haichuan and Liu, Fangming and Pei, Qiangyu and Yuan, Yongjie and Xu, Zichen and Wang, Lin}}, booktitle = {{Proceedings of the ACM Web Conference (WWW)}}, location = {{Singapore}}, publisher = {{ACM}}, title = {{{𝜆Grapher: A Resource-Efficient Serverless System for GNN Serving through Graph Sharing}}}, doi = {{10.1145/3589334.3645383}}, year = {{2024}}, } @article{53531, author = {{Ghafouri, Saeid and Razavi, Kamran and Salmani, Mehran and Sanaee, Alireza and Lorido Botran, Tania and Wang, Lin and Doyle, Joseph and Jamshidi, Pooyan}}, journal = {{Journal of Systems Research (JSys)}}, title = {{{IPA: Inference Pipeline Adaptation to Achieve High Accuracy and Cost-Efficiency}}}, year = {{2024}}, } @inproceedings{55365, author = {{Razavi, Kamran and Davari Fard, Shayan and Karlos, George and Nigade, Vinod and Mühlhäuser, Max and Wang, Lin}}, booktitle = {{Proceedings of the IEEE International Symposium on Computers and Communications (ISCC)}}, location = {{Paris, France}}, title = {{{NetNN: Neural Intrusion Detection System in Programmable Networks (Second Best Paper Award)}}}, year = {{2024}}, } @inproceedings{53095, author = {{Razavi, Kamran and Ghafouri, Saeid and Mühlhäuser, Max and Jamshidi, Pooyan and Wang, Lin}}, booktitle = {{Proceedings of the 4th Workshop on Machine Learning and Systems (EuroMLSys), colocated with EuroSys 2024}}, location = {{Athens, Greece}}, publisher = {{ACM}}, title = {{{Sponge: Inference Serving with Dynamic SLOs Using In-Place Vertical Scaling}}}, doi = {{10.1145/3642970.365583}}, year = {{2024}}, } @inproceedings{50066, author = {{Dou, Feng and Wang, Lin and Chen, Shutong and Liu, Fangming}}, booktitle = {{Proceedings of the IEEE International Conference on Computer Communications (INFOCOM)}}, location = {{Vancouver, Canada}}, publisher = {{IEEE}}, title = {{{X-Stream: A Flexible, Adaptive Video Transformer for Privacy-Preserving Video Stream Analytics}}}, doi = {{10.1109/INFOCOM52122.2024.10621341}}, year = {{2024}}, } @inproceedings{53807, author = {{Liu, Gaosheng and Nigade, Vinod and Bal, Henri and Wang, Lin}}, booktitle = {{Proceedings of the 8th ACM Asia Pacific Workshop on Networking (APNET)}}, location = {{Sydney, Austrialia}}, title = {{{A Little Certainty is All We Need: Discovery and Synchronization Acceleration in Battery-Free IoT}}}, doi = {{10.1145/3663408.3663414}}, year = {{2024}}, } @inproceedings{55366, author = {{Karlos, George and Bal, Henri and Wang, Lin}}, booktitle = {{Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis (SC)}}, location = {{Atlanta, GA}}, title = {{{NetCL: A Unified Programming Framework for In-Network Computing}}}, year = {{2024}}, } @article{55364, author = {{Liu, Gaosheng and Wang, Lin}}, journal = {{IEEE Transactions on Mobile Computing (TMC)}}, title = {{{Data On the Go: Seamless Data Routing for Intermittently-Powered Battery-Free Sensing}}}, doi = {{10.1109/TMC.2024.3429636}}, year = {{2024}}, } @inproceedings{50065, author = {{Blöcher, Marcel and Nedderhut, Nils and Chuprikov, Pavel and Khalili, Ramin and Eugster, Patrick and Wang, Lin}}, booktitle = {{Proceedings of the IEEE International Conference on Computer Communications (INFOCOM)}}, location = {{Vancouver, Canada}}, publisher = {{IEEE}}, title = {{{Train Once Apply Anywhere: Effective Scheduling for Network Function Chains Running on FUMES}}}, doi = {{10.1109/INFOCOM52122.2024.10621125}}, year = {{2024}}, } @inproceedings{56689, author = {{Pei, Qiangyu and Wang, Lin and Zhang, Dong and Yan, Bingheng and Yu, Chen and Liu, Fangming}}, booktitle = {{Proceedings of the 15th ACM Symposium on Cloud Computing (SoCC)}}, location = {{Redmond}}, title = {{{InferCool: Enhancing AI Inference Cooling through Transparent, Non-Intrusive Task Reassignment}}}, year = {{2024}}, } @article{63059, abstract = {{AbstractWhile high accuracy is of paramount importance for deep learning (DL) inference, serving inference requests on time is equally critical but has not been carefully studied especially when the request has to be served over a dynamic wireless network at the edge. In this paper, we propose Jellyfish—a novel edge DL inference serving system that achieves soft guarantees for end-to-end inference latency service-level objectives (SLO). Jellyfish handles the network variability by utilizing both data and deep neural network (DNN) adaptation to conduct tradeoffs between accuracy and latency. Jellyfish features a new design that enables collective adaptation policies where the decisions for data and DNN adaptations are aligned and coordinated among multiple users with varying network conditions. We propose efficient algorithms to continuously map users and adapt DNNs at runtime, so that we fulfill latency SLOs while maximizing the overall inference accuracy. We further investigate dynamic DNNs, i.e., DNNs that encompass multiple architecture variants, and demonstrate their potential benefit through preliminary experiments. Our experiments based on a prototype implementation and real-world WiFi and LTE network traces show that Jellyfish can meet latency SLOs at around the 99th percentile while maintaining high accuracy. }}, author = {{Nigade, Vinod and Bauszat, Pablo and Bal, Henri and Wang, Lin}}, issn = {{0922-6443}}, journal = {{Real-Time Systems}}, number = {{2}}, pages = {{239--290}}, publisher = {{Springer Science and Business Media LLC}}, title = {{{Inference serving with end-to-end latency SLOs over dynamic edge networks}}}, doi = {{10.1007/s11241-024-09418-4}}, volume = {{60}}, year = {{2024}}, } @article{59074, author = {{Hu, Jiahai and Wang, Lin and Wu, Jing and Pei, Qiangyu and Liu, Fangming and Li, Bo}}, issn = {{1389-1286}}, journal = {{Computer Networks}}, publisher = {{Elsevier BV}}, title = {{{A Comparative Measurement Study of Cross-Layer 5G Performance Under Different Mobility Scenarios}}}, doi = {{10.1016/j.comnet.2024.110952}}, volume = {{257}}, year = {{2024}}, } @article{63060, author = {{Wu, Jing and Wang, Lin and Jin, Qirui and Liu, Fangming}}, issn = {{1045-9219}}, journal = {{IEEE Transactions on Parallel and Distributed Systems}}, number = {{2}}, pages = {{280--296}}, publisher = {{Institute of Electrical and Electronics Engineers (IEEE)}}, title = {{{Graft: Efficient Inference Serving for Hybrid Deep Learning With SLO Guarantees via DNN Re-Alignment}}}, doi = {{10.1109/tpds.2023.3340518}}, volume = {{35}}, year = {{2023}}, } @phdthesis{29672, author = {{Schneider, Stefan Balthasar}}, title = {{{Network and Service Coordination: Conventional and Machine Learning Approaches"}}}, doi = {{10.17619/UNIPB/1-1276 }}, year = {{2022}}, } @inproceedings{30236, abstract = {{Recent reinforcement learning approaches for continuous control in wireless mobile networks have shown impressive results. But due to the lack of open and compatible simulators, authors typically create their own simulation environments for training and evaluation. This is cumbersome and time-consuming for authors and limits reproducibility and comparability, ultimately impeding progress in the field. To this end, we propose mobile-env, a simple and open platform for training, evaluating, and comparing reinforcement learning and conventional approaches for continuous control in mobile wireless networks. mobile-env is lightweight and implements the common OpenAI Gym interface and additional wrappers, which allows connecting virtually any single-agent or multi-agent reinforcement learning framework to the environment. While mobile-env provides sensible default values and can be used out of the box, it also has many configuration options and is easy to extend. We therefore believe mobile-env to be a valuable platform for driving meaningful progress in autonomous coordination of wireless mobile networks.}}, author = {{Schneider, Stefan Balthasar and Werner, Stefan and Khalili, Ramin and Hecker, Artur and Karl, Holger}}, booktitle = {{IEEE/IFIP Network Operations and Management Symposium (NOMS)}}, keywords = {{wireless mobile networks, network management, continuous control, cognitive networks, autonomous coordination, reinforcement learning, gym environment, simulation, open source}}, location = {{Budapest}}, publisher = {{IEEE}}, title = {{{mobile-env: An Open Platform for Reinforcement Learning in Wireless Mobile Networks}}}, year = {{2022}}, } @inproceedings{32811, abstract = {{The decentralized nature of multi-agent systems requires continuous data exchange to achieve global objectives. In such scenarios, Age of Information (AoI) has become an important metric of the freshness of exchanged data due to the error-proneness and delays of communication systems. Communication systems usually possess dependencies: the process describing the success or failure of communication is highly correlated when these attempts are ``close'' in some domain (e.g. in time, frequency, space or code as in wireless communication) and is, in general, non-stationary. To study AoI in such scenarios, we consider an abstract event-based AoI process $\Delta(n)$, expressing time since the last update: If, at time $n$, a monitoring node receives a status update from a source node (event $A(n-1)$ occurs), then $\Delta(n)$ is reset to one; otherwise, $\Delta(n)$ grows linearly in time. This AoI process can thus be viewed as a special random walk with resets. The event process $A(n)$ may be nonstationary and we merely assume that its temporal dependencies decay sufficiently, described by $\alpha$-mixing. We calculate moment bounds for the resulting AoI process as a function of the mixing rate of $A(n)$. Furthermore, we prove that the AoI process $\Delta(n)$ is itself $\alpha$-mixing from which we conclude a strong law of large numbers for $\Delta(n)$. These results are new, since AoI processes have not been studied so far in this general strongly mixing setting. This opens up future work on renewal processes with non-independent interarrival times.}}, author = {{Redder, Adrian and Ramaswamy, Arunselvan and Karl, Holger}}, booktitle = {{Proceedings of the 58th Allerton Conference on Communication, Control, and Computing}}, title = {{{Age of Information Process under Strongly Mixing Communication -- Moment Bound, Mixing Rate and Strong Law}}}, year = {{2022}}, } @inproceedings{30793, author = {{Redder, Adrian and Ramaswamy, Arunselvan and Karl, Holger}}, booktitle = {{Proceedings of the 14th International Conference on Agents and Artificial Intelligence}}, publisher = {{SCITEPRESS - Science and Technology Publications}}, title = {{{Multi-agent Policy Gradient Algorithms for Cyber-physical Systems with Lossy Communication}}}, doi = {{10.5220/0010845400003116}}, year = {{2022}}, } @unpublished{30790, abstract = {{Iterative distributed optimization algorithms involve multiple agents that communicate with each other, over time, in order to minimize/maximize a global objective. In the presence of unreliable communication networks, the Age-of-Information (AoI), which measures the freshness of data received, may be large and hence hinder algorithmic convergence. In this paper, we study the convergence of general distributed gradient-based optimization algorithms in the presence of communication that neither happens periodically nor at stochastically independent points in time. We show that convergence is guaranteed provided the random variables associated with the AoI processes are stochastically dominated by a random variable with finite first moment. This improves on previous requirements of boundedness of more than the first moment. We then introduce stochastically strongly connected (SSC) networks, a new stochastic form of strong connectedness for time-varying networks. We show: If for any $p \ge0$ the processes that describe the success of communication between agents in a SSC network are $\alpha$-mixing with $n^{p-1}\alpha(n)$ summable, then the associated AoI processes are stochastically dominated by a random variable with finite $p$-th moment. In combination with our first contribution, this implies that distributed stochastic gradient descend converges in the presence of AoI, if $\alpha(n)$ is summable.}}, author = {{Redder, Adrian and Ramaswamy, Arunselvan and Karl, Holger}}, booktitle = {{arXiv:2201.11343}}, title = {{{Distributed gradient-based optimization in the presence of dependent aperiodic communication}}}, year = {{2022}}, } @unpublished{30791, abstract = {{We present sufficient conditions that ensure convergence of the multi-agent Deep Deterministic Policy Gradient (DDPG) algorithm. It is an example of one of the most popular paradigms of Deep Reinforcement Learning (DeepRL) for tackling continuous action spaces: the actor-critic paradigm. In the setting considered herein, each agent observes a part of the global state space in order to take local actions, for which it receives local rewards. For every agent, DDPG trains a local actor (policy) and a local critic (Q-function). The analysis shows that multi-agent DDPG using neural networks to approximate the local policies and critics converge to limits with the following properties: The critic limits minimize the average squared Bellman loss; the actor limits parameterize a policy that maximizes the local critic's approximation of $Q_i^*$, where $i$ is the agent index. The averaging is with respect to a probability distribution over the global state-action space. It captures the asymptotics of all local training processes. Finally, we extend the analysis to a fully decentralized setting where agents communicate over a wireless network prone to delays and losses; a typical scenario in, e.g., robotic applications.}}, author = {{Redder, Adrian and Ramaswamy, Arunselvan and Karl, Holger}}, booktitle = {{arXiv:2201.00570}}, title = {{{Asymptotic Convergence of Deep Multi-Agent Actor-Critic Algorithms}}}, year = {{2022}}, } @article{32854, author = {{Redder, Adrian and Ramaswamy, Arunselvan and Karl, Holger}}, journal = {{IFAC-PapersOnLine}}, number = {{13}}, pages = {{133–138}}, publisher = {{Elsevier}}, title = {{{Practical Network Conditions for the Convergence of Distributed Optimization}}}, volume = {{55}}, year = {{2022}}, }