Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2511.16225 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914165482848256 |
|---|---|
| author | Croisfelt, Victor de Souza, João Henrique Inacio Pandey, Shashi Raj Soret, Beatriz Popovski, Petar |
| author_facet | Croisfelt, Victor de Souza, João Henrique Inacio Pandey, Shashi Raj Soret, Beatriz Popovski, Petar |
| contents | Connected cyber-physical systems perform inference based on real-time inputs from multiple data streams. Uncertain communication delays across data streams challenge the temporal flow of the inference process. State-of-the-art (SotA) non-blocking inference methods rely on a reference-modality paradigm, requiring one modality input to be fully received before processing, while depending on costly offline profiling. We propose a novel, neuro-inspired non-blocking inference paradigm that primarily employs adaptive temporal windows of integration (TWIs) to dynamically adjust to stochastic delay patterns across heterogeneous streams while relaxing the reference-modality requirement. Our communication-delay-aware framework achieves robust real-time inference with finer-grained control over the accuracy-latency tradeoff. Experiments on the audio-visual event localization (AVEL) task demonstrate superior adaptability to network dynamics compared to SotA approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_16225 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Real-Time Inference for Distributed Multimodal Systems under Communication Delay Uncertainty Croisfelt, Victor de Souza, João Henrique Inacio Pandey, Shashi Raj Soret, Beatriz Popovski, Petar Machine Learning Connected cyber-physical systems perform inference based on real-time inputs from multiple data streams. Uncertain communication delays across data streams challenge the temporal flow of the inference process. State-of-the-art (SotA) non-blocking inference methods rely on a reference-modality paradigm, requiring one modality input to be fully received before processing, while depending on costly offline profiling. We propose a novel, neuro-inspired non-blocking inference paradigm that primarily employs adaptive temporal windows of integration (TWIs) to dynamically adjust to stochastic delay patterns across heterogeneous streams while relaxing the reference-modality requirement. Our communication-delay-aware framework achieves robust real-time inference with finer-grained control over the accuracy-latency tradeoff. Experiments on the audio-visual event localization (AVEL) task demonstrate superior adaptability to network dynamics compared to SotA approaches. |
| title | Real-Time Inference for Distributed Multimodal Systems under Communication Delay Uncertainty |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2511.16225 |