4.8 Article

Deep Fuzzy Cognitive Maps for Interpretable Multivariate Time Series Prediction

Journal

IEEE TRANSACTIONS ON FUZZY SYSTEMS
Volume 29, Issue 9, Pages 2647-2660

Publisher

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TFUZZ.2020.3005293

Keywords

Time series analysis; Predictive models; Fuzzy cognitive maps; Biological neural networks; Heuristic algorithms; Transforms; Deep neural networks; fuzzy cognitive maps (FCM); interpretable prediction; time series prediction

Funding

  1. National Key R&D Program of China [2019YFB2102100]
  2. National Natural Science Foundation of China [61572059, 71531001, 71725002, U1636210]
  3. Fundamental Research Funds for the Central Universities [YWF-20-BJ-J-839]
  4. National Science Foundation of China [71601022]
  5. Youth Top Talent Cultivation Plan Project of Beijing [CITTCD201804036]

Ask authors/readers for more resources

The article introduces a novel extension of Fuzzy Cognitive Map called Deep FCM for multivariate time series forecasting, combining the predictive advantage of deep neural networks and the interpretative advantage of FCM. DFCM utilizes fully connected neural networks and recurrent neural networks to model concept relationships and external factors in the system, and proposes a partial derivative-based method to improve model interpretability.
The fuzzy cognitive map (FCM) is a powerful model for system state prediction and interpretable knowledge representation. Recent years have witnessed the tremendous efforts devoted to enhancing the basic FCM, such as introducing temporal factors, uncertainty or fuzzy rules to improve interpretation, and introducing fuzzy neural networks or wavelets to improve time series prediction. But how to achieve high-precision yet interpretable prediction in cross-domain real-life applications remains a great challenge. In this article, we propose a novel FCM extension called deep FCM (DFCM) for multivariate time series forecasting, in order to take both the advantage of FCM in interpretation and the advantage of deep neural networks in prediction. Specifically, to improve the predictive power, DFCM leverages a fully connected neural network to model connections (relationships) among concepts in a system, and a recurrent neural network to model unknown exogenous factors that have influences on system dynamics. Moreover, to foster model interpretability encumbered by the embedded deep structures, a partial derivative-based approach is proposed to measure the connection strengths between concepts in DFCM. An alternate function gradient descent algorithm is then proposed for parameter inference. The effectiveness of DFCM is validated over four publicly available datasets with the presence of seven baselines. DFCM indeed provides an important clue to building interpretable predictors for real-life applications.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.8
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available