FreqX: Analyze the Attribution Methods in Another Domain
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908291263627264 |
|---|---|
| author | Liu, Zechen Zhang, Feiyang Song, Wei Li, Xiang Wei, Wei |
| author_facet | Liu, Zechen Zhang, Feiyang Song, Wei Li, Xiang Wei, Wei |
| contents | Personalized Federal learning(PFL) allows clients to cooperatively train a personalized model without disclosing their private dataset. However, PFL suffers from Non-IID, heterogeneous devices, lack of fairness, and unclear contribution which urgently need the interpretability of deep learning model to overcome these challenges. These challenges proposed new demands for interpretability. Low cost, privacy, and detailed information. There is no current interpretability method satisfying them. In this paper, we propose a novel interpretability method \emph{FreqX} by introducing Signal Processing and Information Theory. Our experiments show that the explanation results of FreqX contain both attribution information and concept information. FreqX runs at least 10 times faster than the baselines which contain concept information. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_18343 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FreqX: Analyze the Attribution Methods in Another Domain Liu, Zechen Zhang, Feiyang Song, Wei Li, Xiang Wei, Wei Machine Learning Artificial Intelligence Personalized Federal learning(PFL) allows clients to cooperatively train a personalized model without disclosing their private dataset. However, PFL suffers from Non-IID, heterogeneous devices, lack of fairness, and unclear contribution which urgently need the interpretability of deep learning model to overcome these challenges. These challenges proposed new demands for interpretability. Low cost, privacy, and detailed information. There is no current interpretability method satisfying them. In this paper, we propose a novel interpretability method \emph{FreqX} by introducing Signal Processing and Information Theory. Our experiments show that the explanation results of FreqX contain both attribution information and concept information. FreqX runs at least 10 times faster than the baselines which contain concept information. |
| title | FreqX: Analyze the Attribution Methods in Another Domain |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2411.18343 |