MC-TRCM: Observation-Aware Recursive Fusion for Incomplete Mobile and Wearable Mental-Health Feature Views
We propose the Modality-Conditioned Temporal Recursive Context Model (MC-TRCM), which preserves each feature source as a separate token and incorporates missingness as part of the input context.
ProofPaper ↗
Key points
- Public mobile and wearable mental-health datasets often provide summarized feature tables rather than synchronized raw sensor streams.
- Observed sources are encoded with values and missingness summaries, absent sources use learned absence tokens, dataset and task embeddings condition fusion, and a recursive prediction head refines each output over validation-selected steps.
- We evaluated MC-TRCM on six predefined endpoints from DepreST-CAT and Prediction of Severity Change-Depression (PSYCHE-D) using participant-level splits and validation-only model selection.
- Ablations support Feature-wise Linear Modulation, absence tokens, missingness projections, and recursive refinement, while calibration and feature-source controls characterize endpoint behavior.
Sources (1)
- [1]MC-TRCM: Observation-Aware Recursive Fusion for Incomplete Mobile and Wearable Mental-Health Feature ViewsarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 07:38 AM
We propose the Modality-Conditioned Temporal Recursive Context Model (MC-TRCM), which preserves each feature source as a separate token and incorporates missingness as part of the input context.
Public mobile and wearable mental-health datasets often provide summarized feature tables rather than synchronized raw sensor streams.
Extractive summary: sentences quoted from the sources.