A Review and Roadmap of Deep Causal Model from Different Causal Structures and Representations
Chen, Hang, Du, Keqing, Li, Chenguang, Yang, Xinyu
–arXiv.org Artificial Intelligence
The fusion of causal models with deep learning introducing increasingly intricate data sets, such as the causal associations within images or between textual components, has surfaced as a focal research area. Nonetheless, the broadening of original causal concepts and theories to such complex, non-statistical data has been met with serious challenges. In response, our study proposes redefinitions of causal data into three distinct categories from the standpoint of causal structure and representation: definite data, semi-definite data, and indefinite data. Definite data chiefly pertains to statistical data used in conventional causal scenarios, while semi-definite data refers to a spectrum of data formats germane to deep learning, including time-series, images, text, and others. Indefinite data is an emergent research sphere inferred from the progression of data forms by us. To comprehensively present these three data paradigms, we elaborate on their formal definitions, differences manifested in datasets, resolution pathways, and development of research. We summarize key tasks and achievements pertaining to definite and semi-definite data from myriad research undertakings, present a roadmap for indefinite data, beginning with its current research conundrums. Lastly, we classify and scrutinize the key datasets presently utilized within these three paradigms.
arXiv.org Artificial Intelligence
Nov-1-2023
- Country:
- Indian Ocean > Bass Strait (0.04)
- South America > Paraguay
- Oceania > Australia
- Tasmania (0.04)
- North America > United States
- Pennsylvania > Allegheny County > Pittsburgh (0.04)
- Europe
- Germany (0.04)
- United Kingdom > England
- Cambridgeshire > Cambridge (0.04)
- Italy > Marche
- Ancona Province > Ancona (0.04)
- Asia
- Japan > Honshū
- Kantō > Tokyo Metropolis Prefecture > Tokyo (0.14)
- China > Shaanxi Province
- Xi'an (0.04)
- Japan > Honshū
- Genre:
- Overview (1.00)
- Research Report > Experimental Study (0.93)
- Industry:
- Leisure & Entertainment (0.92)
- Banking & Finance (0.92)
- Information Technology (0.67)
- Health & Medicine > Therapeutic Area
- Technology:
- Information Technology
- Sensing and Signal Processing > Image Processing (1.00)
- Artificial Intelligence
- Vision (1.00)
- Natural Language (1.00)
- Cognitive Science (1.00)
- Representation & Reasoning
- Uncertainty (1.00)
- Optimization (0.93)
- Machine Learning
- Statistical Learning (1.00)
- Neural Networks > Deep Learning (1.00)
- Learning Graphical Models > Directed Networks
- Bayesian Learning (1.00)
- Information Technology