SIN: Semantic Inference Network for Few-Shot Streaming Label Learning
- 4 May 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 34 (12) , 9952-9965
Abstract
Streaming label learning aims to model newly emerged labels for multilabel classification systems, which requires plenty of new label data for training. However, in changing environments, only a small amount of new label data can practically be collected. In this work, we formulate and study few-shot streaming label learning (FSLL), which models emerging new labels with only a few annotated examples by utilizing the knowledge learned from past labels. We propose a meta-learning framework, semantic inference network (SIN), which can learn and infer the semantic correlation between new labels and past labels to adapt FSLL tasks from a few examples effectively. SIN leverages label semantic representation to regularize the output space and acquires labelwise meta-knowledge based on gradient-based meta-learning. Moreover, SIN incorporates a novel label decision module with a meta-threshold loss to find the optimal confidence thresholds for each new label. Theoretically, we illustrate that the proposed semantic inference mechanism could constrain the complexity of hypotheses space to reduce the risk of overfitting and achieve better generalizability. Experimentally, extensive empirical results and ablation studies demonstrate the performance of SIN is superior to the prior state-of-the-art methods on FSLL.Keywords
Funding Information
- Australian Research Council Projects (DP-180103424)
- Australian Research Council Projects (FL-170100117, IC-190100031)
This publication has 48 references indexed in Scilit:
- Open challenges for data stream mining researchACM SIGKDD Explorations Newsletter, 2014
- Glove: Global Vectors for Word Representation2014
- Efficient Pairwise Multilabel Classification for Large-Scale Problems in the Legal Domain2008
- The Development of Embodied Cognition: Six Lessons from BabiesArtificial Life, 2005
- A System for new event detection2003
- Dynamic Data Mining2000
- An overview of statistical learning theoryIEEE Transactions on Neural Networks, 1999
- Lifelong Learning Algorithms1998
- Catastrophic Interference in Connectionist Networks: The Sequential Learning Problem1989
- On beyond Zebra: The relation of linguistic and visual informationCognition, 1987