Teaching PPG How not Who: Fixed-Effects Distillation from ECG
ECG is widely used to teach PPG-only models, yet what it teaches is unexamined.
ProofPaper ↗
Key points
- Wearables are valued for tracking how a person's cardiovascular state changes, but ECG-to-PPG distillation mostly learns who the person is.
- A per-recording mean, the trait, holds 40-59% of a frozen ECG teacher's target, and pooled students memorise it without carrying it to new recordings.
- Fixed-effects distillation subtracts each recording's mean from prediction and target, so the trait cancels exactly, while a pooled anchor keeps it.
- Conditioning on the recording turns distillation toward the within-person changes that wearables monitor.
Sources (1)
- [1]Teaching PPG How not Who: Fixed-Effects Distillation from ECGarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 05:16 PM
ECG is widely used to teach PPG-only models, yet what it teaches is unexamined.
Wearables are valued for tracking how a person's cardiovascular state changes, but ECG-to-PPG distillation mostly learns who the person is.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 7, 2026MIMESIS: Learning User Simulators as Training Environments for Interactive Agents
- Oct 7, 2026Composing What Each Teacher Learned: Multi-Teacher On-Policy Distillation through Teacher-Relative Shifts
- Oct 7, 2026On-Policy Distillation Teaches New Skills but Not New Knowledge
- Oct 7, 2026UniSkill: Learning Actor-Aligned Skill Proposals for an Evolving Policy
- Oct 6, 2026Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight
- Oct 6, 2026RISED: Rubrics for Agentic Multi-Environment Selection and Self-Distillation