1)	Task-Specific Embedding Model: embedding functions are different for different tasks and training for a task-specific embedding function only use training data from that specific task.

2)	Task-Invariant Embedding Model: embedding functions are the same for different tasks, and embedding function training is on a large-scale dataset with enough samples.

3)	Hybrid Embedding Model: embedding functions learned from the generic model is adapted by task-specific data.


University of Notre Dame

Embedding learning constrains the searching space $\mathcal{H}$ by mapping each input $x_i\in \mathbb{R}^n$ to a lower dimension space $z_i\in\mathbb{R}^m$, m<n. The mapping process is achieved by an embedding function $f(\cdot)$. And we can achieve better accuracy by using different embedding functions $f_{train}$ and $f_{test}$ for the training and testing set. The prediction on the testing set is made by finding the “closet” training sample compared to one testing sample in the embedded space and predicting the same label for this testing sample as the training sample.

Embedding Learning

Wang, Y., Yao, Q., Kwok, J. T., & Ni, L. M. (2020). Generalizing from a few examples: A survey on few-shot learning. ACM computing surveys (csur), 53(3), 1-34.

Learn Before

Related