R1-2407618
discussion
Discussion on other aspects of AI/ML model and data on AI/ML for NR air-interface
From FUTUREWEI
Summary
FUTUREWEI presents a comprehensive analysis of AI/ML model identification and data management for NR air interface, covering four model identification options, model transfer/delivery mechanisms, and inter-vendor collaboration approaches. The document contains 14 proposals and 3 observations addressing the complexities of two-sided model lifecycle management.
Position
FUTUREWEI advocates for simplified model identification approaches that minimize complexity while supporting two-sided models. They strongly push FOR network-controlled model ID assignment, cell-scoped associated IDs, and deprioritizing complex offline cross-vendor collaboration mechanisms like Case z1/z2/z3. They are AGAINST treating associated IDs as model IDs and support exploring lightweight alternatives that could eliminate the need for model identification entirely through standardized reference models.
Key proposals
- Proposal 1 (Sec 2.1.1): For MI-Option 1, conclude that an associated ID is valid only within a cell, and the network assigns/manages associated IDs
- Proposal 2 (Sec 2.1.1): Conclude that associated ID is not model ID
- Proposal 4 (Sec 2.1.1): For MI-Option 1, conclude that model IDs are assigned only by the NW (Alt. 1)
- Proposal 5 (Sec 2.1.1): For MI-Option 1, revise Step C of AI-Example1 procedure to include cell ID/information in model development
- Proposal 7 (Sec 2.1.2): Clarify the boundary between MI-Option 1 and MI-Option 2, and the relationship between model ID and corresponding dataset
- Proposal 9 (Sec 2.1.2): For MI-Option 2, conclude that UE-side additional condition(s) do not need to be considered
- Proposal 11 (Sec 2.1.3): Support MI-Option 3 with further study of its procedures and specification impact, based on model transfer Case z4
- Proposal 12 (Sec 2.1.4): Consider MI-Option 4 as a valid option only if the relationship between the reference model and multiple derived models can be clarified
- Proposal 13 (Sec 2.2): Study the feasibility of supporting two-sided models without model identification
- Proposal 14 (Sec 2.3): Deprioritize Case z1 as it does not provide clear benefit over Case y