{"paper":{"title":"Decentralized Multi-Channel MANET Power Optimization Using Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Graph neural networks enable decentralized transmit power optimization across multiple channels in mobile ad hoc networks.","cross_cats":[],"primary_cat":"cs.NI","authors_text":"Michael Segal, Nir Shlezinger, Tomer Alter","submitted_at":"2026-05-12T18:02:47Z","abstract_excerpt":"The increasing demand for mobile ad hoc networks (MANETs) calls for decentralized mechanisms that can allocate transmit power across nodes and channels under stringent resource constraints. Existing optimization-based approaches, however, do not account for expected settings where each link includes multiple channels (e.g., multi-band signaling). Motivated by recent advances in machine learning for distributed optimization, we propose MANET-GNN, a graph neural network (GNN)-based algorithm for decentralized power allocation in multi-channel MANETs. MANET-GNN explicitly exploits the network top"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"MANET-GNN achieves high-throughput multi-channel communication across diverse MANET scenarios.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a message-passing GNN trained unsupervised on graph topology will generalize to unseen topologies and channel conditions while remaining robust to noisy CSI.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MANET-GNN is a GNN-based method for decentralized multi-channel power optimization in MANETs that achieves high throughput via unsupervised training on network topology.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Graph neural networks enable decentralized transmit power optimization across multiple channels in mobile ad hoc networks.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"5bbb9eea73b0ff7f47e9ada740dfa66a2ec2ed2d330b9c75538739cbc14e6135"},"source":{"id":"2605.12612","kind":"arxiv","version":1},"verdict":{"id":"07e67087-5c4b-4422-8ac0-654b28c3bda9","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:22:01.352811Z","strongest_claim":"MANET-GNN achieves high-throughput multi-channel communication across diverse MANET scenarios.","one_line_summary":"MANET-GNN is a GNN-based method for decentralized multi-channel power optimization in MANETs that achieves high throughput via unsupervised training on network topology.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a message-passing GNN trained unsupervised on graph topology will generalize to unseen topologies and channel conditions while remaining robust to noisy CSI.","pith_extraction_headline":"Graph neural networks enable decentralized transmit power optimization across multiple channels in mobile ad hoc networks."},"references":{"count":31,"sample":[{"doi":"","year":2006,"title":"B. Tavli and W. Heinzelman,Mobile Ad hoc networks. Springer, 2006","work_id":"94a655c0-3cf0-4b09-ac1e-6d56abfde7f3","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Software- defined networking meets software-defined radio in mobile ad hoc networks: state of the art and future directions,","work_id":"2843ebe8-288c-431b-9006-fadaab1affec","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"A multi-channel MAC protocol with retrodirective array antennas in flying ad hoc networks,","work_id":"069c3b7e-a057-4f06-9df4-cdf9ed7133e4","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"A novel MIMO-OFDM based MAC protocol for V ANETs,","work_id":"3d3cc50f-3a48-4ce7-931f-7784ebac22cd","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Joint fairness and efficiency optimization for CSMA/CA-based multi-user MIMO UA V ad hoc networks,","work_id":"5ca695ef-3473-4b28-a9ea-df2a181af540","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":31,"snapshot_sha256":"27e662c5c28d215819b524002255b3a8c59890aa05141ba3704f8ea80d60701f","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}