Adaptive Information Coordination for Context-Aware International Event Forecasting with Temporal Knowledge Graphs
- 1School of Economics and Management, Beijing University of Chemical Technology, Beijing 100029, China
- 2China People’s Police University, Langfang 065000, China
Abstract
Context-aware international event forecasting must preserve context-specific evidence while drawing on related interactions across semantic boundaries. We propose the hierarchical adaptive fusion and separation network (HA-AFSNet), which learns this balance before temporal encoding. A history-conditioned coefficient jointly fuses entity and relation states, linking information allocation to the participant-ranking objective. The evaluated task ranks candidate participants conditional on semantic context labels derived from articles associated with the queried events. Across five seeds on three GDELT regional graphs, HA-AFSNet improves mean reciprocal rank (MRR) over SeCoGD by 9.73–11.35%. Compared with a learned static gate, the mean MRR gains are 0.0109–0.0149, with positive pointwise 95% paired Student intervals under the stated distributional assumptions. With only five seed pairs, this statistical evidence is limited and conditional on the evaluated splits. The conditioning branch accounts for 1.68–1.78% of the full model’s parameters. Complete test-period coefficient trajectories show how the allocation varies across dates and receiving contexts. These results support history-conditioned information allocation for participant ranking within the supplied event-associated context labels.
Related
- Informed forecasting: Leveraging auxiliary knowledge to boost large language model performance on time series forecasting
- A Theory of Information Architecture for Networked Decisions: Freshness, Locality, and Coordination
- When Does Text Inform? Benchmarking Information-Theoretic Metrics for Multimodal Time-Series Forecasting
- Combining Weather Forecast Aggregation and State-Space Models for Adaptive Probabilistic Electricity Load Forecasting
- State-aware adaptive multimodal fusion for ultra-short-term solar irradiance forecasting using sky cloud images
BibTeX
@article{zhang2026adaptive,
title = {{Adaptive Information Coordination for Context-Aware International Event Forecasting with Temporal Knowledge Graphs}},
author = {Yunbo Zhang and Jun Wu and Yu Wang and Jiayi Song and Jing Liu and Jicheng Niu},
journal = {Mathematics},
year = {2026},
month = oct,
doi = {10.3390/math14213876},
url = {https://www.mdpi.com/2227-7390/14/21/3876},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Adaptive Information Coordination for Context-Aware International Event Forecasting with Temporal Knowledge Graphs
AU - Yunbo Zhang
AU - Jun Wu
AU - Yu Wang
AU - Jiayi Song
AU - Jing Liu
AU - Jicheng Niu
PY - 2026
DA - 2026/10/23
JO - Mathematics
DO - 10.3390/math14213876
UR - https://www.mdpi.com/2227-7390/14/21/3876
AB - Context-aware international event forecasting must preserve context-specific evidence while drawing on related interactions across semantic boundaries. We propose the hierarchical adaptive fusion and separation network (HA-AFSNet), which learns this balance before temporal encoding. A history-conditioned coefficient jointly fuses entity and relation states, linking information allocation to the participant-ranking objective. The evaluated task ranks candidate participants conditional on semantic context labels derived from articles associated with the queried events. Across five seeds on three GDELT regional graphs, HA-AFSNet improves mean reciprocal rank (MRR) over SeCoGD by 9.73–11.35%. Compared with a learned static gate, the mean MRR gains are 0.0109–0.0149, with positive pointwise 95% paired Student intervals under the stated distributional assumptions. With only five seed pairs, this statistical evidence is limited and conditional on the evaluated splits. The conditioning branch accounts for 1.68–1.78% of the full model’s parameters. Complete test-period coefficient trajectories show how the allocation varies across dates and receiving contexts. These results support history-conditioned information allocation for participant ranking within the supplied event-associated context labels.
SN - 2227-7390
ER -