R1-2409397
discussion
Discussion on AI/ML for CSI prediction
From Huawei
Huawei's prior position on
9.1.3
at
RAN1#118bis
· AI-synthesized, paraphrased
verify sources →
Strongly advocates against introducing associated IDs or network-side indications for CSI prediction consistency, arguing they are unnecessary and create privacy risks. Proposes UE-side performance monitoring as a sufficient implementation-based solution instead.
Summary
Huawei argues against introducing network-side indications, such as associated IDs, to ensure consistency between training and inference for UE-side AI/ML models in CSI prediction, citing feasibility issues and proprietary disclosure risks. The document presents 5 observations and 2 proposals, asserting that generalized performance can be achieved with mixed datasets and that consistency can instead be managed via UE-side performance monitoring.
Position
Huawei presents a technical case against the necessity and feasibility of introducing associated IDs or other NW-side indications for CSI prediction consistency. They argue that the massive number of impacting factors, such as antenna layout and down tilt angles, makes categorization by the network difficult and risks proprietary disclosure of network planning information. Huawei contends that unlike beam management or positioning, CSI prediction models achieve sufficient generalized performance using mixed datasets (Generalization Case 3), rendering explicit consistency indications unnecessary. Instead, they propose that consistency be ensured through UE-side performance monitoring in an implementation manner, allowing the UE to select the best-matching model without network signaling overhead.
Key proposals
- Proposal 1 (Sec 2.2): No need to introduce indications from NW (e.g., explicit indication or associated ID) for ensuring consistency between training/inference for CSI prediction.
- Proposal 2 (Sec 2.3): The consistency can be achieved by performance monitoring at UE side with an implementation manner.
Revision chain
2 versions in this meeting · oldest first
-
R1-2409397 ← you are here discussion revised
-
Discussion on AI/ML for CSI prediction