Semantic Inference Network for Few-shot Streaming Label Learning

Streaming label learning aims to model newly emerged labels for multi-label 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 label-wise meta-knowledge based on the 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 demonstrate 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 illustrate the superior performance of SIN over the prior state-of-the-art methods on FSLL.