Cognitively-Inspired Emergent Communication via Knowledge Graphs for Assisting the Visually Impaired
This work addresses the problem of real-time navigation for visually impaired individuals by providing a fast, adaptive, and human-aligned solution, though it appears incremental as it builds on existing emergent communication frameworks.
The paper tackled the trade-off between latency and semantic richness in assistive systems for visually impaired individuals by introducing VAG-EC, a framework that uses knowledge graphs and attention mechanisms to enable compact, interpretable symbolic languages, resulting in improved performance in Topographic Similarity and Context Independence compared to traditional methods.
Assistive systems for visually impaired individuals must deliver rapid, interpretable, and adaptive feedback to facilitate real-time navigation. Current approaches face a trade-off between latency and semantic richness: natural language-based systems provide detailed guidance but are too slow for dynamic scenarios, while emergent communication frameworks offer low-latency symbolic languages but lack semantic depth, limiting their utility in tactile modalities like vibration. To address these limitations, we introduce a novel framework, Cognitively-Inspired Emergent Communication via Knowledge Graphs (VAG-EC), which emulates human visual perception and cognitive mapping. Our method constructs knowledge graphs to represent objects and their relationships, incorporating attention mechanisms to prioritize task-relevant entities, thereby mirroring human selective attention. This structured approach enables the emergence of compact, interpretable, and context-sensitive symbolic languages. Extensive experiments across varying vocabulary sizes and message lengths demonstrate that VAG-EC outperforms traditional emergent communication methods in Topographic Similarity (TopSim) and Context Independence (CI). These findings underscore the potential of cognitively grounded emergent communication as a fast, adaptive, and human-aligned solution for real-time assistive technologies. Code is available at https://github.com/Anonymous-NLPcode/Anonymous_submission/tree/main.