Causal Discovery and Knowledge Injection for Contestable Neural Networks (with Appendices)
Neural networks have proven to be effective at solving machine learning tasks but it is unclear whether they learn any relevant causal relationships, while their black-box nature makes it difficult for modellers to understand and debug them. We propose a novel method overcoming these issues by allowing a two-way interaction whereby neural-network-empowered machines can expose the underpinning learnt causal graphs and humans can contest the machines by modifying the causal graphs before re-injecting them into the machines. The learnt models are guaranteed to conform to the graphs and adhere to expert knowledge, some of which can also be given up-front. By building a window into the model behaviour and enabling knowledge injection, our method allows practitioners to debug networks based on the causal structure discovered from the data and underpinning the predictions. Experiments with real and synthetic tabular data show that our method improves predictive performance up to 2.4x while producing parsimonious networks, up to 7x smaller in the input layer, compared to SOTA regularised networks.
Code (1)
Tasks
Causal DiscoverySimilar Papers 제목 키워드 기반
Integrating Background Knowledge for Scalable Causal Discovery
Expert background knowledge is often available in practical applications of causal discovery. Such constraints on the true causal graph can help causal discovery in terms of identifiability of causal effects and accuracy…
Domain Knowledge in A*-Based Causal Discovery
Causal discovery has become a vital tool for scientists and practitioners wanting to discover causal relationships from observational data. While most previous approaches to causal discovery have implicitly assumed that …
Causal DiscoveryDKCD: Domain Knowledge-Enhanced Causal Discovery from Unstructured Data
Causal discovery from unstructured data is a challenging yet underexplored task in high-expertise domains such as healthcare, finance, and education. Existing methods typically leverage the general knowledge of large lan…
General KnowledgeWeakly-supervised causal discovery based on fuzzy knowledge and complex data complementarity
Causal discovery based on observational data is important for deciphering the causal mechanism behind complex systems. However, the effectiveness of existing causal discovery methods is limited due to inferior prior know…
Causal DiscoveryComputational EfficiencySDVDiag: Multimodal Causal Discovery for Online Diagnosis in Software-defined Vehicles
The transition toward software-defined vehicles concentrates an increasing share of vehicle functionality into distributed software services, where failures propagate through service dependencies and the surface symptom …