Year of Graduation
Optimal Graph Traversal with Deep Reinforcement Learning
Recently similarity graphs became the leading paradigm for efficient nearest neighbor search, outperforming traditional tree-based and LSH-based methods. Similarity graphs perform the search via greedy routing: a query traverses the graph and in each vertex moves to the adjacent vertex that is the closest to this query. In practice, similarity graphs are often susceptible to local minima, when queries do not reach its nearest neighbors, getting stuck in suboptimal vertices. In this paper we propose to learn the routing function that overcomes local minima via incorporating information about the graph global structure. In particular, The vertices of this graph are supplemented with additional representations that are learned to provide the optimal routing from the start vertex to the query nearest neighbor. By thorough experiments, it was demonstrated that the proposed learnable routing successfully diminishes the local minima problem and significantly improves the overall search performance.