Semantic-Aware Task Clustering for Constructive and Cooperative Multi-Tasking
Cooperative multi-task semantic communication (CMT-SemCom) improves task execution performance by leveraging shared representations. However, as we demonstrated in [1], cooperative multi-tasking can be either constructive or destructive, depending on the semantic relationships among tasks. To ensure constructive cooperation, we propose a semantic-aware task clustering method for CMT-SemCom. We have formulated a sequential multi-stage optimization problem in which semantically aligned tasks are clustered once after a short initial training phase, and then end-to-end (E2E) joint training is cond
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%microsoft/semantic-kernel →
“Fuzzy title match (0.73): “Semantic-Aware Task Clustering for Constructive and Cooperat” ≈ “microsoft/semantic-kernel””
- LinkedLinked via arxiv author · 85%Ahmad Halimi Razlighi →
“Semantic-Aware Task Clustering for Constructive and Cooperative Multi-Tasking”
- LinkedLinked via arxiv author · 85%Maximilian H. V. Tillmann →
“Semantic-Aware Task Clustering for Constructive and Cooperative Multi-Tasking”
- LinkedLinked via arxiv author · 85%Edgar Beck →
“Semantic-Aware Task Clustering for Constructive and Cooperative Multi-Tasking”
- LinkedLinked via arxiv author · 85%Bho Matthiesen →
“Semantic-Aware Task Clustering for Constructive and Cooperative Multi-Tasking”
- LinkedLinked via arxiv author · 85%Armin Dekorsy →
“Semantic-Aware Task Clustering for Constructive and Cooperative Multi-Tasking”