1 / 14

Label Embedding Trees for Large Multi-class Tasks

Label Embedding Trees for Large Multi-class Tasks. Samy Bengio Jason Weston David Grangier. Presented by Zhengming Xing. Outline. Introduction Label Trees Label Embeddings Experiment result. Introduction. Large scale problem: the number of example Feature dimension Number of class.

Télécharger la présentation

Label Embedding Trees for Large Multi-class Tasks

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Label Embedding Trees for Large Multi-class Tasks SamyBengio Jason Weston David Grangier Presented by Zhengming Xing

  2. Outline • Introduction • Label Trees • Label Embeddings • Experiment result

  3. Introduction Large scale problem: the number of example Feature dimension Number of class Main idea: propose a fast and memory saving multi-class classifier for large dataset based on trees structure method

  4. Introduction Label Tree: Indexed nodes: Edges: Label Predictors: Label sets: The root contain all classes, and each child label set is a subset of its parent K is the number of classes Disjoint tree: any two nodes at the same depth cannot share any labels.

  5. Introduction Classifying an example:

  6. Label Trees Tree loss I is the indicator function is the depth in the tree of the final prediction for x

  7. Label tree Learning with fixed label tree: N,E,L chosen in advance Goal: minimize the tree loss over the variables F Given training data Relaxation 1 Replace indicator function with hinge loss and Relaxation 2

  8. Label tree Learning label tree structure for disjoint tree Basic idea: group together labels into the same label set that are likely to be confused at test time. Treat A as the affinity matrix and apply the steps similar to spectral clustering

  9. Label embeddings define is a k-dimensional vector with a 1 in the yth position and 0 otherwise solve Problem : how to learn W, V

  10. Label embeddings Method 1: Learn V The same two steps of algorithm 2 minimize Learn W minimize

  11. Label embedding Method 2: join learn W and V minimize Combine all the methods discussed above minimize

  12. Experiment Dataset

  13. Experiment

  14. Experiment

More Related