Model Adaptation via Model Interpolation and Boosting for Web Search Ranking
This work addresses model adaptation for web search ranking, offering incremental improvements in handling data distribution shifts.
The paper tackles the problem of adapting web search ranking models to different data distributions by comparing model interpolation and boosting methods, finding that model interpolation performs best on open test sets with dissimilar data, while boosting excels on closed test sets with similar data but suffers from instability on open sets.
This paper explores two classes of model adaptation methods for Web search ranking: Model Interpolation and error-driven learning approaches based on a boosting algorithm. The results show that model interpolation, though simple, achieves the best results on all the open test sets where the test data is very different from the training data. The tree-based boosting algorithm achieves the best performance on most of the closed test sets where the test data and the training data are similar, but its performance drops significantly on the open test sets due to the instability of trees. Several methods are explored to improve the robustness of the algorithm, with limited success.