Online Structured Meta-learning
This work addresses the challenge of heterogeneous task learning in online platforms, offering an incremental improvement over existing meta-learning methods.
The paper tackled the problem of sub-optimal performance in online meta-learning when tasks are heterogeneous by proposing an online structured meta-learning framework that disentangles the meta-learner into a hierarchical graph, enabling quick adaptation through relevant knowledge blocks. Experiments on three datasets demonstrated its effectiveness and interpretability for both homogeneous and heterogeneous tasks.
Learning quickly is of great importance for machine intelligence deployed in online platforms. With the capability of transferring knowledge from learned tasks, meta-learning has shown its effectiveness in online scenarios by continuously updating the model with the learned prior. However, current online meta-learning algorithms are limited to learn a globally-shared meta-learner, which may lead to sub-optimal results when the tasks contain heterogeneous information that are distinct by nature and difficult to share. We overcome this limitation by proposing an online structured meta-learning (OSML) framework. Inspired by the knowledge organization of human and hierarchical feature representation, OSML explicitly disentangles the meta-learner as a meta-hierarchical graph with different knowledge blocks. When a new task is encountered, it constructs a meta-knowledge pathway by either utilizing the most relevant knowledge blocks or exploring new blocks. Through the meta-knowledge pathway, the model is able to quickly adapt to the new task. In addition, new knowledge is further incorporated into the selected blocks. Experiments on three datasets demonstrate the effectiveness and interpretability of our proposed framework in the context of both homogeneous and heterogeneous tasks.