Confidence Optimization for Probabilistic Encoding
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908461983334400 |
|---|---|
| author | Xia, Pengjiu Huang, Yidian Wei, Wenchao Tan, Yuwen |
| author_facet | Xia, Pengjiu Huang, Yidian Wei, Wenchao Tan, Yuwen |
| contents | Probabilistic encoding introduces Gaussian noise into neural networks, enabling a smooth transition from deterministic to uncertain states and enhancing generalization ability. However, the randomness of Gaussian noise distorts point-based distance measurements in classification tasks. To mitigate this issue, we propose a confidence optimization probabilistic encoding (CPE) method that improves distance reliability and enhances representation learning. Specifically, we refine probabilistic encoding with two key strategies: First, we introduce a confidence-aware mechanism to adjust distance calculations, ensuring consistency and reliability in probabilistic encoding classification tasks. Second, we replace the conventional KL divergence-based variance regularization, which relies on unreliable prior assumptions, with a simpler L2 regularization term to directly constrain variance. The method we proposed is model-agnostic, and extensive experiments on natural language classification tasks demonstrate that our method significantly improves performance and generalization on both the BERT and the RoBERTa model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_16881 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Confidence Optimization for Probabilistic Encoding Xia, Pengjiu Huang, Yidian Wei, Wenchao Tan, Yuwen Machine Learning Artificial Intelligence Probabilistic encoding introduces Gaussian noise into neural networks, enabling a smooth transition from deterministic to uncertain states and enhancing generalization ability. However, the randomness of Gaussian noise distorts point-based distance measurements in classification tasks. To mitigate this issue, we propose a confidence optimization probabilistic encoding (CPE) method that improves distance reliability and enhances representation learning. Specifically, we refine probabilistic encoding with two key strategies: First, we introduce a confidence-aware mechanism to adjust distance calculations, ensuring consistency and reliability in probabilistic encoding classification tasks. Second, we replace the conventional KL divergence-based variance regularization, which relies on unreliable prior assumptions, with a simpler L2 regularization term to directly constrain variance. The method we proposed is model-agnostic, and extensive experiments on natural language classification tasks demonstrate that our method significantly improves performance and generalization on both the BERT and the RoBERTa model. |
| title | Confidence Optimization for Probabilistic Encoding |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2507.16881 |