DeepAI AI Chat
Log In Sign Up

ProtoInfoMax: Prototypical Networks with Mutual Information Maximization for Out-of-Domain Detection

by   Iftitahu Ni'mah, et al.
TU Eindhoven

The ability to detect Out-of-Domain (OOD) inputs has been a critical requirement in many real-world NLP applications since the inclusion of unsupported OOD inputs may lead to catastrophic failure of systems. However, it remains an empirical question whether current algorithms can tackle such problem reliably in a realistic scenario where zero OOD training data is available. In this study, we propose ProtoInfoMax, a new architecture that extends Prototypical Networks to simultaneously process In-Domain (ID) and OOD sentences via Mutual Information Maximization (InfoMax) objective. Experimental results show that our proposed method can substantially improve performance up to 20 also show that ProtoInfoMax is less prone to typical over-confidence Error of Neural Networks, leading to more reliable ID and OOD prediction outcomes.


page 1

page 2

page 3

page 4


Supervision Adaptation Balances In-Distribution Generalization and Out-of-Distribution Detection

When there is a discrepancy between in-distribution (ID) samples and out...

S^3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximization

Recently, significant progress has been made in sequential recommendatio...

Monitoring Shortcut Learning using Mutual Information

The failure of deep neural networks to generalize to out-of-distribution...

Cross-Domain Sentiment Classification With Contrastive Learning and Mutual Information Maximization

Contrastive learning (CL) has been successful as a powerful representati...

Diverse Melody Generation from Chinese Lyrics via Mutual Information Maximization

In this paper, we propose to adapt the method of mutual information maxi...