Papers with Prototypical Networks
Meta-learning Pathologies from Radiology Reports using Variance Aware Prototypical Networks (2022.emnlp-industry)
Copied to clipboard
| Challenge: | Existing methods for fewshot learning require a large number of in-domain labeled examples for fine tuning. |
| Approach: | They propose to extend the Prototypical Networks for few-shot text classification by replacing Gaussian class prototypes with a regularization term that encourages the examples to be clustered near the appropriate class centroids. |
| Outcome: | The proposed method outperforms baselines on 13 public and 4 internal datasets and detects potential out-of-distribution (OOD) data points during deployment. |
ProtoInfoMax: Prototypical Networks with Mutual Information Maximization for Out-of-Domain Detection (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to detect out-of-domain (OOD) inputs are limited and lack data. |
| Approach: | They propose a new architecture that extends Prototypical Networks to process in-domain and OOD sentences via Mutual Information Maximization objective. |
| Outcome: | The proposed method significantly improves performance up to 20% for OOD detection in low resource settings of text classification. |
PROTAUGMENT: Unsupervised diverse short-texts paraphrasing for intent detection meta-learning (2021.acl-long)
Copied to clipboard
| Challenge: | Recent research considers few-shot intent detection as a meta-learning problem because of labeled data scarcity and the number of classes involved. |
| Approach: | They propose a meta-learning algorithm for short texts classification that limits overfitting on the bias introduced by the few-shots classification objective at each episode. |
| Outcome: | The proposed algorithm limits overfitting on the bias introduced by the few-shots classification objective at each episode. |
HyperNetwork-based Decoupling to Improve Model Generalization for Few-Shot Relation Extraction (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies cannot generalize well to unseen relations using Prototypical Networks . current approaches are dependent on large amount of labeled data and cannot deal with unseense relations well. |
| Approach: | They propose a HyperNetwork-based Decoupling approach to improve FSRE generalization . they propose FSre models with an encoder, network generator and refined classifiers . |
| Outcome: | The proposed method improves the generalization of few-shot relation extraction models. |
Few-Shot Emotion Recognition in Conversation with Sequential Prototypical Networks (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on dyadic human-human interactions focus on conversations without specific business objectives. |
| Approach: | They propose a method to detect emotions in a live chat customer service . they propose 'ProtoSeq' for conversational emotion classification using different languages . |
| Outcome: | The proposed method is competitive even when applied to other ones. |
Prototypical Reward Network for Data-Efficient Model Alignment (2024.acl-long)
Copied to clipboard
| Challenge: | Reinforcement Learning from Human Feedback (RLHF) is a reward model that fine-tunes Large Language Models (LLMs) by utilizing Prototypical Networks. |
| Approach: | They propose a framework utilizing Prototypical Networks to enhance reward models under limited human feedback, enabling more stable and reliable structural learning from fewer samples. |
| Outcome: | The proposed framework improves reward models under limited human feedback, surpassing traditional methods, especially in data-limited scenarios. |