Interactive Concept Bottleneck Models
Authors: Kushal Chauhan, Rishabh Tiwari, Jan Freyberg, Pradeep Shenoy, Krishnamurthy Dvijotham
AAAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We demonstrate that a simple policy combining concept prediction uncertainty and influence of the concept on the final prediction achieves strong performance and outperforms static approaches as well as active feature acquisition methods proposed in the literature. We show that the interactive CBM can achieve accuracy gains of 5-10% with only 5 interactions over competitive baselines on the Caltech-UCSD Birds, Che Xpert and OAI datasets. 4 Experiments |
| Researcher Affiliation | Industry | Kushal Chauhan, Rishabh Tiwari, Jan Freyberg, Pradeep Shenoy, Krishnamurthy Dvijotham Google Research {kushalchauhan, rishabhtiwari,janfreyberg,shenoypradeep,dvij}@google.com |
| Pseudocode | Yes | Algorithm 1: Policy Rollout |
| Open Source Code | Yes | 1Code is available at https://github.com/google-research/google research/tree/master/interactive cbms |
| Open Datasets | Yes | CUB (Caltech-UCSD Birds): This dataset contains pictures of birds coupled with human-labeled concept attributes identifying prominent characteristics (wing color, beak length, undertail color, etc.) (Wah et al. 2011). CHEXPERT: This dataset contains chest X-rays accompanied by binary concept labels extracted from a report generated by a radiologist, with the goal of predicting whether the X-ray was normal or abnormal (Irvin et al. 2019). |
| Dataset Splits | Yes | For each experiment, we split the data into 3 sets: train, validation, and test the details are available in Table 1. ... Table 1: Details of the datasets used in our experiments. Data splits train 4,796 val 1,198 test 5,794 |
| Hardware Specification | No | No specific hardware details such as GPU models, CPU types, or memory specifications used for running experiments were mentioned in the paper. |
| Software Dependencies | No | No specific software dependencies with version numbers (e.g., library or framework versions) were explicitly stated in the paper. |
| Experiment Setup | No | The paper describes the general training and evaluation process, including dataset splits and the types of CBMs used, but does not provide specific hyperparameter values (e.g., learning rate, batch size, number of epochs, optimizer settings) in the main text. |