Salvato in:
| Autori principali: | , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2409.13684 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909700432330752 |
|---|---|
| author | Jin, Helen Havaldar, Shreya Kim, Chaehyeon Xue, Anton You, Weiqiu Qu, Helen Gatti, Marco Hashimoto, Daniel A Jain, Bhuvnesh Madani, Amin Sako, Masao Ungar, Lyle Wong, Eric |
| author_facet | Jin, Helen Havaldar, Shreya Kim, Chaehyeon Xue, Anton You, Weiqiu Qu, Helen Gatti, Marco Hashimoto, Daniel A Jain, Bhuvnesh Madani, Amin Sako, Masao Ungar, Lyle Wong, Eric |
| contents | Feature-based methods are commonly used to explain model predictions, but these methods often implicitly assume that interpretable features are readily available. However, this is often not the case for high-dimensional data, and it can be hard even for domain experts to mathematically specify which features are important. Can we instead automatically extract collections or groups of features that are aligned with expert knowledge? To address this gap, we present FIX (Features Interpretable to eXperts), a benchmark for measuring how well a collection of features aligns with expert knowledge. In collaboration with domain experts, we propose FIXScore, a unified expert alignment measure applicable to diverse real-world settings across cosmology, psychology, and medicine domains in vision, language, and time series data modalities. With FIXScore, we find that popular feature-based explanation methods have poor alignment with expert-specified knowledge, highlighting the need for new methods that can better identify features interpretable to experts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_13684 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | The FIX Benchmark: Extracting Features Interpretable to eXperts Jin, Helen Havaldar, Shreya Kim, Chaehyeon Xue, Anton You, Weiqiu Qu, Helen Gatti, Marco Hashimoto, Daniel A Jain, Bhuvnesh Madani, Amin Sako, Masao Ungar, Lyle Wong, Eric Machine Learning Artificial Intelligence Feature-based methods are commonly used to explain model predictions, but these methods often implicitly assume that interpretable features are readily available. However, this is often not the case for high-dimensional data, and it can be hard even for domain experts to mathematically specify which features are important. Can we instead automatically extract collections or groups of features that are aligned with expert knowledge? To address this gap, we present FIX (Features Interpretable to eXperts), a benchmark for measuring how well a collection of features aligns with expert knowledge. In collaboration with domain experts, we propose FIXScore, a unified expert alignment measure applicable to diverse real-world settings across cosmology, psychology, and medicine domains in vision, language, and time series data modalities. With FIXScore, we find that popular feature-based explanation methods have poor alignment with expert-specified knowledge, highlighting the need for new methods that can better identify features interpretable to experts. |
| title | The FIX Benchmark: Extracting Features Interpretable to eXperts |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2409.13684 |