Publications
32 peer-reviewed papers and 9 preprints or papers under review. Full and current lists are on Google Scholar and DBLP.
2026
-
OJ-ITS
Federated Learning for Traffic Flow Prediction With Synthetic Data Augmentation
IEEE Open Journal of Intelligent Transportation Systems, 7, 445–459
BibTeX
@article{orozco2026federated, title = {Federated Learning for Traffic Flow Prediction With Synthetic Data Augmentation}, author = {Orozco, Fermin and Wen, Hongkai and Porto Buarque de Gusm{\~a}o, Pedro and Wahlstr{\"o}m, Johan and Luo, Man}, journal = {IEEE Open Journal of Intelligent Transportation Systems}, volume = {7}, pages = {445--459}, year = {2026}, doi = {10.1109/OJITS.2026.3659531} } -
Clust. Comput.
Robust Federated Learning Aggregation for Highly Heterogeneous Data
Cluster Computing, 29(15), 875
BibTeX
@article{bae2026robust, title = {Robust Federated Learning Aggregation for Highly Heterogeneous Data}, author = {Bae, Jang Hoon and Park, Byoungjun and Porto Buarque de Gusm{\~a}o, Pedro and Kim, Minchul and Kim, Minhoe}, journal = {Cluster Computing}, volume = {29}, number = {15}, pages = {875}, year = {2026}, publisher = {Springer}, doi = {10.1007/s10586-026-06716-3} } -
arXiv
Omni-C: Compressing Heterogeneous Modalities into a Single Dense Encoder
arXiv preprint arXiv:2603.05528
2025
-
FLEdge-AI
Efficient Federated Model Aggregation through Neural Velocity
FLEdge-AI '25: Proceedings of the Federated Learning and Edge AI for Privacy and Mobility, ACM MobiCom
BibTeX
@inproceedings{dalmasso2025efficient, title = {Efficient Federated Model Aggregation through Neural Velocity}, author = {Dalmasso, Gianluca and Porto Buarque de Gusm{\~a}o, Pedro and Fiandrotti, Attilio and Grangetto, Marco}, booktitle = {Proceedings of the 2025 Federated Learning and Edge AI for Privacy and Mobility (FLEdge-AI '25)}, publisher = {Association for Computing Machinery}, year = {2025}, doi = {10.1145/3737899.3768519} } -
arXiv
arXiv preprint arXiv:2511.11778
-
CCNC
2025 IEEE 22nd Consumer Communications & Networking Conference (CCNC)
BibTeX
@inproceedings{park2025improving, title = {Improving Semi-Supervised Federated Learning with Limited Labeled Data via Adaptive Batchsize and Pseudo Labeling}, author = {Park, Byoungjun and Porto Buarque de Gusm{\~a}o, Pedro and Kim, Minhoe}, booktitle = {2025 IEEE 22nd Consumer Communications \& Networking Conference (CCNC)}, publisher = {IEEE}, year = {2025}, doi = {10.1109/CCNC54725.2025.10976067} }
2024
-
New Phytol.
New Phytologist, 245(4), 1512–1527
BibTeX
@article{lambretfrotte2024increased, title = {Increased Chloroplast Occupancy in Bundle Sheath Cells of Rice {hap3H} Mutants Revealed by {Chloro-Count}: A New Deep Learning--Based Tool}, author = {Lambret-Frotte, J. and Porto Buarque de Gusm{\~a}o, Pedro and Smith, G. and Lo, S.-F. and Yu, S.-M. and Hendron, R. and Kelly, S. and Langdale, J.}, journal = {New Phytologist}, volume = {245}, number = {4}, pages = {1512--1527}, year = {2024}, doi = {10.1111/nph.20332} } -
ACCV
FedRepOpt: Gradient Re-parametrized Optimizers in Federated Learning
Computer Vision – ACCV 2024, Lecture Notes in Computer Science, vol. 15479
BibTeX
@inproceedings{lau2024fedrepopt, title = {{FedRepOpt}: Gradient Re-parametrized Optimizers in Federated Learning}, author = {Lau, Kin Wai and Rehman, Yasar Abbas Ur and Porto Buarque de Gusm{\~a}o, Pedro and Po, Lai-Man and Ma, Lan and Xie, Yuyang}, booktitle = {Computer Vision -- ACCV 2024}, editor = {Cho, Minsu and Laptev, Ivan and Tran, Du and Yao, Angela and Zha, Hongbin}, series = {Lecture Notes in Computer Science}, volume = {15479}, publisher = {Springer, Singapore}, year = {2025}, doi = {10.1007/978-981-96-0966-6_5} } -
arXiv
arXiv preprint arXiv:2402.10191
2023
-
JMLR
A First Look into the Carbon Footprint of Federated Learning
Journal of Machine Learning Research, 24
-
USENIX Sec.
FedVal: Different Good or Different Bad in Federated Learning
32nd USENIX Security Symposium
-
ICCV
IEEE/CVF International Conference on Computer Vision
-
VTC
Decentralized Training of 3D Lane Detection with Automatic Labeling Using HD Maps
97th IEEE Vehicular Technology Conference (VTC2023-Spring)
-
EuroMLSys
Can Fair Federated Learning Reduce the Need for Personalisation?
3rd Workshop on Machine Learning and Systems (EuroMLSys)
-
arXiv
High-throughput Simulation of Federated Learning via Resource-Aware Client Placement
arXiv preprint arXiv:2306.17453
-
arXiv
vFedSec: Efficient Secure Aggregation for Vertical Federated Learning via Secure Layer
arXiv preprint arXiv:2305.16794
-
arXiv
Privacy in Multimodal Federated Human Activity Recognition
arXiv preprint arXiv:2305.12134
-
arXiv
Efficient Vertical Federated Learning with Secure Aggregation
arXiv preprint arXiv:2305.11236
2022
-
ICLR
ZeroFL: Efficient On-Device Training for Federated Learning with Local Sparsity
International Conference on Learning Representations
-
ECCV
Federated Self-supervised Learning for Video Understanding
European Conference on Computer Vision
-
ICASSP
End-to-End Speech Recognition from Federated Acoustic Models
IEEE International Conference on Acoustics, Speech and Signal Processing
-
SLT
Match to Win: Analysing Sequences Lengths for Efficient Self-Supervised Learning in Speech and Audio
IEEE Spoken Language Technology Workshop
-
FedEdge
Protea: Client Profiling within Federated Systems using Flower
1st ACM Workshop on Data Privacy and Federated Learning Technologies for Mobile Edge Network
-
T-RO
Graph-Based Thermal-Inertial SLAM With Probabilistic Neural Networks
IEEE Transactions on Robotics
- Neural Netw.
2021
-
DistributedML
Secure Aggregation for Federated Learning in Flower
2nd ACM International Workshop on Distributed Machine Learning (DistributedML)
-
MLSys WS
On-device Federated Learning with Flower
On-device Intelligence Workshop at MLSys
-
ICRA
RadarLoc: Learning to Relocalize in FMCW Radar
IEEE International Conference on Robotics and Automation
2020
-
arXiv
Flower: A Friendly Federated Learning Research Framework
arXiv preprint arXiv:2007.14390
-
SenSys
milliEgo: Single-chip mmWave Radar Aided Egomotion Estimation via Deep Sensor Fusion
18th ACM Conference on Embedded Networked Sensor Systems
-
RA-L
DeepTIO: A Deep Thermal-Inertial Odometry With Visual Hallucination
IEEE Robotics and Automation Letters, 5(2)
-
Sensors J.
Sensor Fusion for Magneto-Inductive Navigation
IEEE Sensors Journal, 20(1)
2019
-
ICCV
Distilling Knowledge From a Deep Pose Regressor Network
IEEE/CVF International Conference on Computer Vision
-
IROS
DeepPCO: End-to-End Point Cloud Odometry through Deep Parallel Neural Network
IEEE/RSJ International Conference on Intelligent Robots and Systems
-
ICRA
Learning Monocular Visual Odometry through Geometry-Aware Curriculum Learning
International Conference on Robotics and Automation
-
ICRA
International Conference on Robotics and Automation
-
DCOSS
Map-aided Navigation for Emergency Searches
15th International Conference on Distributed Computing in Sensor Systems
2017
-
PhD
Feature Extraction using MPEG-CDVS and Deep Learning with Application to Robotic Navigation and Image Classification
PhD thesis, Politecnico di Torino
2016
-
arXiv
Fast Training of Convolutional Neural Networks via Kernel Rescaling
arXiv preprint arXiv:1610.03623
-
CoDIT
Gabor Filter Based Image Representation for Object Classification
International Conference on Control, Decision and Information Technologies
2015
-
MMSP
Loop Detection in Robotic Navigation using MPEG CDVS
17th IEEE International Workshop on Multimedia Signal Processing
2011
-
ICME
Statistical Modelling of Outliers for Fast Visual Search
IEEE International Conference on Multimedia and Expo