Goal-oriented Tensor: Beyond Age of Information Towards Semantics-Empowered Goal-Oriented Communications
Aimin Li, Shaohua Wu, Sumei Sun, and Jie Cao

TL;DR
This paper introduces the Goal-oriented Tensor (GoT), a new metric for semantic-aware, goal-driven communication systems, and develops a co-design framework for sampling and decision-making that outperforms traditional Age of Information metrics.
Contribution
It proposes the Goal-oriented Tensor (GoT) as a novel metric and formulates a decentralized decision process, along with an efficient algorithm for goal-oriented communication optimization.
Findings
GoT effectively quantifies semantic mismatches impacting decision utility.
The co-designed sampler and decision-maker outperform AoI-based methods in simulations.
The proposed approach achieves higher goal utility with sparser sampling rates.
Abstract
Optimizations premised on open-loop metrics such as Age of Information (AoI) indirectly enhance the system's decision-making utility. We therefore propose a novel closed-loop metric named Goal-oriented Tensor (GoT) to directly quantify the impact of semantic mismatches on goal-oriented decision-making utility. Leveraging the GoT, we consider a sampler & decision-maker pair that works collaboratively and distributively to achieve a shared goal of communications. We formulate a two-agent infinite-horizon Decentralized Partially Observable Markov Decision Process (Dec-POMDP) to conjointly deduce the optimal deterministic sampling policy and decision-making policy. To circumvent the curse of dimensionality in obtaining an optimal deterministic joint policy through Brute-Force-Search, a sub-optimal yet computationally efficient algorithm is developed. This algorithm is predicated on the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAge of Information Optimization
