Name
Abstract | ||
|---|---|---|
This paper addresses the task of explaining anomalous predictions of a black-box regression model. When using a black-box model, such as one to predict building energy consumption from many sensor measurements, we often have a situation where some observed samples may significantly deviate from their prediction. It may be due to a sub-optimal black-box model, or simply because those samples are outliers. In either case, one would ideally want to compute a "responsibility score" indicative of the extent to which an input variable is responsible for the anomalous output. In this work, we formalize this task as a statistical inverse problem: Given model deviation from the expected value, infer the responsibility score of each of the input variables. We propose a new method called likelihood compensation (LC), which is founded on the likelihood principle and computes a correction to each input variable. To the best of our knowledge, this is the first principled framework that computes a responsibility score for real valued anomalous model deviations. We apply our approach to a real-world building energy prediction task and confirm its utility based on expert feedback. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1609/aaai.v35i5.16535 | THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE |
DocType | Volume | ISSN |
Conference | 35 | 2159-5399 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Tsuyoshi Ide | 1 | 6 | 1.05 |
| Amit Dhurandhar | 2 | 70 | 19.33 |
| Jiri Navratil | 3 | 0 | 0.34 |
| Moninder Singh | 4 | 381 | 105.12 |
| Naoki Abe | 5 | 1345 | 131.56 |