@unpublished{SongLiuChenetal.2022, author = {Song, Rui and Liu, Dai and Chen, Dave Zhenyu and Festag, Andreas and Trinitis, Carsten and Schulz, Martin and Knoll, Alois}, title = {Federated Learning via Decentralized Dataset Distillation in Resource Constrained Edge Environments}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2208.11311}, year = {2022}, abstract = {In federated learning, all networked clients contribute to the model training cooperatively. However, with model sizes increasing, even sharing the trained partial models often leads to severe communication bottlenecks in underlying networks, especially when communicated iteratively. In this paper, we introduce a federated learning framework FedD3 requiring only one-shot communication by integrating dataset distillation instances. Instead of sharing model updates in other federated learning approaches, FedD3 allows the connected clients to distill the local datasets independently, and then aggregates those decentralized distilled datasets (e.g. a few unrecognizable images) from networks for model training. Our experimental results show that FedD3 significantly outperforms other federated learning frameworks in terms of needed communication volumes, while it provides the additional benefit to be able to balance the trade-off between accuracy and communication cost, depending on usage scenario or target dataset. For instance, for training an AlexNet model on CIFAR-10 with 10 clients under non-independent and identically distributed (Non-IID) setting, FedD3 can either increase the accuracy by over 71\% with a similar communication volume, or save 98\% of communication volume, while reaching the same accuracy, compared to other one-shot federated learning approaches.}, language = {en} } @unpublished{SongLiangXiaetal.2025, author = {Song, Rui and Liang, Chenwei and Xia, Yan and Zimmer, Walter and Cao, Hu and Caesar, Holger and Festag, Andreas and Knoll, Alois}, title = {CoDa-4DGS: Dynamic Gaussian Splatting with Context and Deformation Awareness for Autonomous Driving}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2503.06744}, year = {2025}, abstract = {Dynamic scene rendering opens new avenues in autonomous driving by enabling closed-loop simulations with photorealistic data, which is crucial for validating end-to-end algorithms. However, the complex and highly dynamic nature of traffic environments presents significant challenges in accurately rendering these scenes. In this paper, we introduce a novel 4D Gaussian Splatting (4DGS) approach, which incorporates context and temporal deformation awareness to improve dynamic scene rendering. Specifically, we employ a 2D semantic segmentation foundation model to self-supervise the 4D semantic features of Gaussians, ensuring meaningful contextual embedding. Simultaneously, we track the temporal deformation of each Gaussian across adjacent frames. By aggregating and encoding both semantic and temporal deformation features, each Gaussian is equipped with cues for potential deformation compensation within 3D space, facilitating a more precise representation of dynamic scenes. Experimental results show that our method improves 4DGS's ability to capture fine details in dynamic scene rendering for autonomous driving and outperforms other self-supervised methods in 4D reconstruction and novel view synthesis. Furthermore, CoDa-4DGS deforms semantic features with each Gaussian, enabling broader applications.}, language = {en} } @inproceedings{SongFestagJagtapetal.2024, author = {Song, Rui and Festag, Andreas and Jagtap, Abhishek Dinkar and Bialdyga, Maximilian and Yan, Zhiran and Otte, Maximilian and Sadashivaiah, Sanath Tiptur and Knoll, Alois}, title = {First Mile: An Open Innovation Lab for Infrastructure-Assisted Cooperative Intelligent Transportation Systems}, booktitle = {2024 IEEE Intelligent Vehicles Symposium (IV)}, publisher = {IEEE}, address = {Piscataway}, isbn = {979-8-3503-4881-1}, doi = {https://doi.org/10.1109/IV55156.2024.10588500}, pages = {1635 -- 1642}, year = {2024}, language = {en} } @inproceedings{SongLiuChenetal.2023, author = {Song, Rui and Liu, Dai and Chen, Dave Zhenyu and Festag, Andreas and Trinitis, Carsten and Schulz, Martin and Knoll, Alois}, title = {Federated Learning via Decentralized Dataset Distillation in Resource-Constrained Edge Environments}, booktitle = {IJCNN 2023 Conference Proceedings}, publisher = {IEEE}, address = {Piscataway}, isbn = {978-1-6654-8867-9}, doi = {https://doi.org/10.1109/IJCNN54540.2023.10191879}, year = {2023}, language = {en} } @inproceedings{AgrawalSongDoychevaetal.2023, author = {Agrawal, Shiva and Song, Rui and Doycheva, Kristina and Knoll, Alois and Elger, Gordon}, title = {Intelligent Roadside Infrastructure for Connected Mobility}, booktitle = {Smart Cities, Green Technologies, and Intelligent Transport Systems: 11th International Conference, SMARTGREENS 2022 and 8th International Conference, VEHITS 2022: Revised Selected Papers}, editor = {Klein, Cornel and Jarke, Matthias and Ploeg, Jeroen and Helfert, Markus and Berns, Karsten and Gusikhin, Oleg}, publisher = {Springer}, address = {Cham}, isbn = {978-3-031-37470-8}, issn = {1865-0937}, doi = {https://doi.org/10.1007/978-3-031-37470-8_6}, pages = {134 -- 157}, year = {2023}, language = {en} } @article{SongZhouLyuetal.2023, author = {Song, Rui and Zhou, Liguo and Lyu, Lingjuan and Festag, Andreas and Knoll, Alois}, title = {ResFed: Communication-Efficient Federated Learning With Deep Compressed Residuals}, volume = {11}, journal = {IEEE Internet of Things Journal}, number = {6}, publisher = {IEEE}, address = {New York}, issn = {2327-4662}, doi = {https://doi.org/10.1109/JIOT.2023.3324079}, pages = {9458 -- 9472}, year = {2023}, abstract = {Federated learning allows for cooperative training among distributed clients by sharing their locally learned model parameters, such as weights or gradients. However, as model size increases, the communication bandwidth required for deployment in wireless networks becomes a bottleneck. To address this, we propose a residual-based federated learning framework (ResFed) that transmits residuals instead of gradients or weights in networks. By predicting model updates at both clients and the server, residuals are calculated as the difference between updated and predicted models and contain more dense information than weights or gradients. We find that the residuals are less sensitive to an increasing compression ratio than other parameters, and hence use lossy compression techniques on residuals to improve communication efficiency for training in federated settings. With the same compression ratio, ResFed outperforms current methods (weight- or gradient-based federated learning) by over 1.4× on federated data sets, including MNIST, FashionMNIST, SVHN, CIFAR-10, CIFAR-100, and FEMNIST, in client-to-server communication, and can also be applied to reduce communication costs for server-to-client communication.}, language = {en} } @article{HegdeSongFestag2023, author = {Hegde, Anupama and Song, Rui and Festag, Andreas}, title = {Radio Resource Allocation in 5G-NR V2X: A Multi-Agent Actor-Critic Based Approach}, volume = {11}, journal = {IEEE Access}, publisher = {IEEE}, address = {New York}, issn = {2169-3536}, doi = {https://doi.org/10.1109/ACCESS.2023.3305267}, pages = {87225 -- 87244}, year = {2023}, abstract = {The efficiency of radio resource allocation and scheduling procedures in Cellular Vehicle-to-X (Cellular V2X) communication networks directly affects link quality in terms of latency and reliability. However, owing to the continuous movement of vehicles, it is impossible to have a centralized coordinating unit at all times to manage the allocation of radio resources. In the unmanaged mode of the fifth generation new radio (5G-NR) V2X, the sensing-based semi-persistent scheduling (SB-SPS) loses its effectiveness when V2X data messages become aperiodic with varying data sizes. This leads to misinformed resource allocation decisions among vehicles and frequent resource collisions. To improve resource selection, this study formulates the Cellular V2X communication network as a decentralized multi-agent networked markov decision process (MDP) where each vehicle agent executes an actor-critic-based radio resource scheduler. Developing further the actor-critic methodology for the radio resource allocation problem in Cellular V2X, two variants are derived: independent actor-critic (IAC) and shared experience actor-critic (SEAC). Results from simulation studies indicate that the actor-critic schedulers improve reliability, achieving a 15-20\% higher probability of reception under high vehicular density scenarios with aperiodic traffic patterns.}, language = {en} } @unpublished{SongZhouLyuetal.2022, author = {Song, Rui and Zhou, Liguo and Lyu, Lingjuan and Festag, Andreas and Knoll, Alois}, title = {ResFed: Communication Efficient Federated Learning by Transmitting Deep Compressed Residuals}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2212.05602}, year = {2022}, language = {en} } @inproceedings{FestagSong2021, author = {Festag, Andreas and Song, Rui}, title = {Analysis of Existing Approaches for Information Sharing in Cooperative Intelligent Transport Systems}, booktitle = {FISITA World Congress 2021}, subtitle = {SENSORIS and V2X Messaging}, publisher = {FISITA}, address = {Bishops Stortford}, url = {https://www.fisita.com/library/f2020-acm-012}, year = {2021}, language = {en} } @inproceedings{SongHegdeSeneletal.2022, author = {Song, Rui and Hegde, Anupama and Senel, Numan and Knoll, Alois and Festag, Andreas}, title = {Edge-Aided Sensor Data Sharing in Vehicular Communication Networks}, booktitle = {2022 IEEE 95th Vehicular Technology Conference: (VTC2022-Spring) Proceedings}, publisher = {IEEE}, address = {Piscataway (NJ)}, isbn = {978-1-6654-8243-1}, issn = {2577-2465}, doi = {https://doi.org/10.1109/VTC2022-Spring54318.2022.9860849}, year = {2022}, language = {en} } @inproceedings{SongZhouLakshminarasimhanetal.2022, author = {Song, Rui and Zhou, Liguo and Lakshminarasimhan, Venkatnarayanan and Festag, Andreas and Knoll, Alois}, title = {Federated Learning Framework Coping with Hierarchical Heterogeneity in Cooperative ITS}, booktitle = {2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)}, publisher = {IEEE}, address = {Piscataway}, isbn = {978-1-6654-6880-0}, pages = {3502 -- 3508}, year = {2022}, language = {en} } @article{ZhouSongChenetal.2023, author = {Zhou, Liguo and Song, Rui and Chen, Guang and Festag, Andreas and Knoll, Alois}, title = {Residual encoding framework to compress DNN parameters for fast transfer}, volume = {2023}, pages = {110815}, journal = {Knowledge-Based Systems}, number = {277}, publisher = {Elsevier}, address = {Amsterdam}, issn = {1872-7409}, doi = {https://doi.org/10.1016/j.knosys.2023.110815}, year = {2023}, language = {en} } @inproceedings{SongLyuJiangetal.2023, author = {Song, Rui and Lyu, Lingjuan and Jiang, Wei and Festag, Andreas and Knoll, Alois}, title = {V2X-Boosted Federated Learning for Cooperative Intelligent Transportation Systems with Contextual Client Selection}, booktitle = {CoPerception: Collaborative Perception and Learning, ICRA 2023 workshop}, url = {https://drive.google.com/file/d/1-OQAeNryd7-lksCTuWnhhyydpFSnw5On/view?usp=share_link}, year = {2023}, language = {en} } @unpublished{SongLiangCaoetal.2024, author = {Song, Rui and Liang, Chenwei and Cao, Hu and Yan, Zhiran and Zimmer, Walter and Gross, Markus and Festag, Andreas and Knoll, Alois}, title = {Collaborative Semantic Occupancy Prediction with Hybrid Feature Fusion in Connected Automated Vehicles}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2402.07635}, year = {2024}, abstract = {Collaborative perception in automated vehicles leverages the exchange of information between agents, aiming to elevate perception results. Previous camera-based collaborative 3D perception methods typically employ 3D bounding boxes or bird's eye views as representations of the environment. However, these approaches fall short in offering a comprehensive 3D environmental prediction. To bridge this gap, we introduce the first method for collaborative 3D semantic occupancy prediction. Particularly, it improves local 3D semantic occupancy predictions by hybrid fusion of (i) semantic and occupancy task features, and (ii) compressed orthogonal attention features shared between vehicles. Additionally, due to the lack of a collaborative perception dataset designed for semantic occupancy prediction, we augment a current collaborative perception dataset to include 3D collaborative semantic occupancy labels for a more robust evaluation. The experimental findings highlight that: (i) our collaborative semantic occupancy predictions excel above the results from single vehicles by over 30\%, and (ii) models anchored on semantic occupancy outpace state-of-the-art collaborative 3D detection techniques in subsequent perception applications, showcasing enhanced accuracy and enriched semantic-awareness in road environments.}, language = {en} } @article{SongXuFestagetal.2023, author = {Song, Rui and Xu, Runsheng and Festag, Andreas and Ma, Jiaqi and Knoll, Alois}, title = {FedBEVT: Federated Learning Bird's Eye View Perception Transformer in Road Traffic Systems}, volume = {9}, journal = {IEEE Transactions on Intelligent Vehicles}, number = {1}, publisher = {IEEE}, address = {New York}, issn = {2379-8904}, doi = {https://doi.org/10.1109/TIV.2023.3310674}, pages = {958 -- 969}, year = {2023}, abstract = {Bird's eye view (BEV) perception is becoming increasingly important in the field of autonomous driving. It uses multi-view camera data to learn a transformer model that directly projects the perception of the road environment onto the BEV perspective. However, training a transformer model often requires a large amount of data, and as camera data for road traffic are often private, they are typically not shared. Federated learning offers a solution that enables clients to collaborate and train models without exchanging data but model parameters. In this paper, we introduce FedBEVT, a federated transformer learning approach for BEV perception. In order to address two common data heterogeneity issues in FedBEVT: (i) diverse sensor poses, and (ii) varying sensor numbers in perception systems, we propose two approaches - Federated Learning with Camera-Attentive Personalization (FedCaP) and Adaptive Multi-Camera Masking (AMCM), respectively. To evaluate our method in real-world settings, we create a dataset consisting of four typical federated use cases. Our findings suggest that FedBEVT outperforms the baseline approaches in all four use cases, demonstrating the potential of our approach for improving BEV perception in autonomous driving.}, language = {en} } @inproceedings{AgrawalSongKohlietal.2022, author = {Agrawal, Shiva and Song, Rui and Kohli, Akhil and Korb, Andreas and Andre, Maximilian and Holzinger, Erik and Elger, Gordon}, title = {Concept of Smart Infrastructure for Connected Vehicle Assist and Traffic Flow Optimization}, booktitle = {Proceedings of the 8th International Conference on Vehicle Technology and Intelligent Transport Systems}, editor = {Ploeg, Jeroen and Helfert, Markus and Berns, Karsten and Gusikhin, Oleg}, publisher = {SciTePress}, address = {Set{\´u}bal}, isbn = {978-989-758-573-9}, issn = {2184-495X}, doi = {https://doi.org/10.5220/0011068800003191}, pages = {360 -- 367}, year = {2022}, abstract = {The smart infrastructure units can play a vital role to develop smart cities of the future and in assisting automated vehicles on the road by providing extended perception and timely warnings to avoid accidents. This paper focuses on the development of such an infrastructure unit, that is specifically designed for a pedestrian crossing junction. It can control traffic lights at the junction by real-time environment perception through its sensors and can optimize the flow of vehicles and passing vulnerable road users (VRUs). Moreover, it can assist on-road vehicles by providing real-time information and critical warnings via a v2x module. This paper further describes different use-cases of the work, all major hardware components involved in the development of smart infrastructure unit, referred to as an edge, different sensor fusion approaches using the camera, radar, and lidar mounted on the edge for environment perception, various modes of communication including v2x, system design}, language = {en} } @unpublished{SongLyuJiangetal.2023, author = {Song, Rui and Lyu, Lingjuan and Jiang, Wei and Festag, Andreas and Knoll, Alois}, title = {V2X-Boosted Federated Learning for Cooperative Intelligent Transportation Systems with Contextual Client Selection}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2305.11654}, year = {2023}, abstract = {Machine learning (ML) has revolutionized transportation systems, enabling autonomous driving and smart traffic services. Federated learning (FL) overcomes privacy constraints by training ML models in distributed systems, exchanging model parameters instead of raw data. However, the dynamic states of connected vehicles affect the network connection quality and influence the FL performance. To tackle this challenge, we propose a contextual client selection pipeline that uses Vehicle-to-Everything (V2X) messages to select clients based on the predicted communication latency. The pipeline includes: (i) fusing V2X messages, (ii) predicting future traffic topology, (iii) pre-clustering clients based on local data distribution similarity, and (iv) selecting clients with minimal latency for future model aggregation. Experiments show that our pipeline outperforms baselines on various datasets, particularly in non-iid settings.}, language = {en} } @inproceedings{JagtapSongSadashivaiahetal.2025, author = {Jagtap, Abhishek Dinkar and Song, Rui and Sadashivaiah, Sanath Tiptur and Festag, Andreas}, title = {V2X-Gaussians: Gaussian Splatting for Multi-Agent Cooperative Dynamic Scene Reconstruction}, booktitle = {2025 IEEE Intelligent Vehicles Symposium (IV)}, publisher = {IEEE}, address = {Piscataway}, isbn = {979-8-3315-3803-3}, doi = {https://doi.org/10.1109/IV64158.2025.11097436}, pages = {1033 -- 1039}, year = {2025}, language = {en} }