CoSSA: Correlation-Structure Shift Adapter for Cross-City Urban Forecasting

Md Muntaqim Meherab

Keywords: Urban forecasting, Cross-city transfer learning, Spatiotemporal modeling, Domain adaptation, Correlation structure alignment, Traffic prediction

TL;DR: We propose CoSSA, a simple adapter that transfers urban forecasting models across cities by aligning correlation structure—improving accuracy without node or ontology alignment.

Abstract:

Urban forecasting rarely transfers across cities because sensor IDs, layouts, and
metadata seldom align. Ontology mapping is brittle and does not scale. We present
CoSSA, a lightweight adapter that transfers models by aligning latent correlation
structure, without ontology or node alignment. CoSSA uses a Temporal CNN
with a dynamic similarity graph and a Similarity-Structure Matching (SSM) loss
to match pairwise correlation geometry between source and target latent states
using unlabeled target data. This ontology-free criterion preserves relations
(who moves with whom) rather than identities. On METR-LA (N =207) → PEMS-BAY
(N =325), CoSSA improves over a source-only baseline by ≈8.2% MAE and
≈6.5% RMSE on held-out target tests, while remaining simple and scalable. The
method is few-shot ready and robust to schema mismatch.

Submission Number: 46