Timezone: »

 
Poster
Embedding Inference for Structured Multilabel Prediction
Farzaneh Mirzazadeh · Siamak Ravanbakhsh · Nan Ding · Dale Schuurmans

Mon Dec 07 04:00 PM -- 08:59 PM (PST) @ 210 C #43
in Poster Session »

A key bottleneck in structured output prediction is the need for inference during training and testing, usually requiring some form of dynamic programming. Rather than using approximate inference or tailoring a specialized inference method for a particular structure---standard responses to the scaling challenge---we propose to embed prediction constraints directly into the learned representation. By eliminating the need for explicit inference a more scalable approach to structured output prediction can be achieved, particularly at test time. We demonstrate the idea for multi-label prediction under subsumption and mutual exclusion constraints, where a relationship to maximum margin structured output prediction can be established. Experiments demonstrate that the benefits of structured output training can still be realized even after inference has been eliminated.

[ PDF] 

Author Information

Farzaneh Mirzazadeh (University of Alberta)
Siamak Ravanbakhsh (University of Alberta)
Nan Ding (Google)
Dale Schuurmans (Alberta)

More from the Same Authors