Evaluation
Link Prediction
Suggest Edits
For link prediction tasks, Kumo provides F1@K, MAP@K, Precision@K, Recall@K (for K = 1, 10, and 100), as well as the following:
Normalized Discounted Cumulative Gain (NDCG) is calculated by:
where _reli _is the graded relevance of the result at position i.
Mean Average Precision (MAP) is calculated by:
where MAP is calculated by finding the average precision(AP) for each class, and then averaging over the number of classes.
Mean Reciprocal Rank (MRR) is calculated by:
where _ranki _refers to the rank position of the first relevant item for the i-th query.
where _reli _is the graded relevance of the result at position i.
Mean Average Precision (MAP) is calculated by:
where MAP is calculated by finding the average precision(AP) for each class, and then averaging over the number of classes.
Mean Reciprocal Rank (MRR) is calculated by:
where _ranki _refers to the rank position of the first relevant item for the i-th query.