Locality-Sensitive Hashing.ppt

Locality-Sensitive Hashing Basic Technique Hamming-LSH Applications Finding Similar Pairs Suppose we have in main memory data representing a large number of objects. May be the objects themselves (e.g., summaries of faces). May be signatures as in minhashing. We want to compare each to each, finding those pairs that are sufficiently similar. Candidate Generation From Minhash Signatures Pick a similarity threshold s, a fraction 1. A pair of columns c and d is a candidate pair if their signatures agree in at least fraction s of the rows. I.e., M (i, c ) = M (i, d ) for at least fraction s values of i. Candidate Generation --- (2) For images, a pair of vectors is a candidate if they differ by at most a small threshold t in at least s % of the components. For entity records, a pair is a candidate if the sum of similarity scores of corresponding components exceeds a threshold. The Problem with Checking for Candidates While the signatures of all columns may fit in main memory, comparing the signatures of all pairs of columns is quadratic in the number of columns. Example: 106 columns implies 5*1011 comparisons. At 1 microsecond/comparison: 6 days. Solutions Divide-Compute-Merge (DCM) uses external sorting, merging. Locality-Sensitive Hashing (LSH) can be carried out in main memory, but admits some false negatives. Hamming LSH --- a variant LSH method. Divide-Compute-Merge Designed for “shingles” and docs. At each stage, divide data into batches that fit in main memory. Operate on individual batches and write out partial results to disk. Merge partial results from disk. DCM Steps DCM Summary Start with the pairs shingleId, docId. Sort by shingleId. In a sequential scan, generate triplets docId1, docId2, 1 for pairs of docs that share a shingle. Sort on docId1, docId2. Merge triplets with common docIds to generate triplets of the form docId1,docId2,count. Output document pairs with count threshold. Some Optimizations “Invert and Pair” is the most expensive ste