Jie Ren, Mingjie Li, Qirui Chen, Huiqi Deng, Quanshi Zhang
Published 2021-11-11, updated 2022-10-17Version 4
This paper aims to show that the inference logic of a deep model can be faithfully approximated as a sparse, symbolic causal graph. Such a causal graph potentially bridges the gap between connectionism and symbolism. To this end, the faithfulness of the causal graph is theoretically guaranteed, because we show that the causal graph can well mimic the model's output on an exponential number of different masked samples. Besides, such a causal graph can be further simplified and re-written as an And-Or graph (AOG), which explains the logical relationship between interactive concepts encoded by the deep model, without losing much explanation accuracy.
ROBY: Evaluating the Robustness of a Deep Model by its Decision Boundaries
Multi-task learning with deep model based reinforcement learning
Restructuring, Pruning, and Adjustment of Deep Models for Parallel Distributed Inference
![QR code for arXiv:2111.06206 [cs.LG]](http://oss.arxitics.com/images/favicon.svg)