Embedding Inference for Structured Multilabel Prediction
Annual Conference on Neural Information Processing Systems(2015)
摘要
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.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络