Papers › Conditional Temporal Neural Processes with Covariance Loss

Conditional Temporal Neural Processes with Covariance Loss

22 Jun 2021ICML 2021 6archive 2025-07-28

Boseon Yoo, Jiwoo Lee, Janghoon Ju, Seijun Chung, Soyeon Kim, Jaesik Choi

We introduce a novel loss function, Covariance Loss, which is conceptually equivalent to conditional neural processes and has a form of regularization so that is applicable to many kinds of neural networks. With the proposed loss, mappings from input variables to target variables are highly affected by dependencies of target variables as well as mean activation and mean dependencies of input and target variables. This nature enables the resulting neural networks to become more robust to noisy observations and recapture missing dependencies from prior information. In order to show the validity of the proposed loss, we conduct extensive sets of experiments on real-world datasets with state-of-the-art models and discuss the benefits and drawbacks of the proposed Covariance Loss.

Paper PDF Code

Code

boseon-ai/Conditional-Temporal-Neural-Processes-with-Covariance-Loss official report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Time Series Forecasting Traffic Prediction

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Time Series Forecasting	PeMSD7	STGCN-Cov	9 steps MAE	3.51	#1 of 7	Archive leaderboard	report
Traffic Prediction	METR-LA	GWNET-Cov	MAE @ 12 step	3.50	#16 of 20	Archive leaderboard	report
Traffic Prediction	METR-LA	GWNET-Cov	MAE @ 3 step	2.69	#16 of 20	Archive leaderboard	report
Traffic Prediction	PEMS-BAY	GWNET-Cov	MAE @ 12 step	1.91	#10 of 16	Archive leaderboard	report
Traffic Prediction	PEMS-BAY	GWNET-Cov	RMSE	4.40	#10 of 16	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections