Uploaded June 2024 | Updated September 2026, 6 hours ago
Liana Patel is a Ph.D. student at Stanford University who is the lead author of ACORN, a breakthrough in Approximate Nearest Neighbor Search with Filters! Also joining the podcast is Abdel Rodriguez, a Vector Index Researcher and Engineer at Weaviate. This podcast dives into all sorts of details behind ACORN. Starting with how Liana developed her interest in Approximate Nearest Neighbor Search algorithms and then transitioning into how ACORN differs from previous approaches, the Two-Hop Neighborhood Heuristic, Predicate Subgraphs, Experimental Details, and many more topics! Major thank you to Liana and Abdel for joining the podcast, this was such a fun conversation packed with insights about Proximity Graph algorithms for Vector Search with Filtering!
Read more about ACORN here! - arxiv.org/pdf/2403.04871
Chapters
0:00 Welcome Liana and Abdel
0:40 What lead you to Approxiomate Nearest Neighbor Search?
2:05 What lead you to Filtered Vector Search?
3:50 ACORN, an overview
10:35 How to connect disparate regions?
12:40 Two-Hop Neighborhood Heuristic
20:48 ACORN and Pre-Filtering
22:30 Strengthening a Predicate Subgraph
24:26 Hyperparameter Recommendations
27:28 Time Complexity Analysis of ACORN
29:45 Importance of the Hierarchy in ACORN
33:30 Selective Pruning
38:05 Experimental Analysis and Vector / Filter Correlation
47:34 Observability for Vector Databases
49:45 Compound AI Systems
Liana Patel is a Ph.D. student at Stanford University who is the lead author of ACORN, a breakthrough in Approximate Nearest Neighbor Search with Filters! Also joining the podcast is Abdel Rodriguez, a Vector Index Researcher and Engineer at Weaviate. This podcast dives into all sorts of details behind ACORN. Starting with how Liana developed her interest in Approximate Nearest Neighbor Search algorithms and then transitioning into how ACORN differs from previous approaches, the Two-Hop Neighborhood Heuristic, Predicate Subgraphs, Experimental Details, and many more topics! Major thank you to Liana and Abdel for joining the podcast, this was such a fun conversation packed with insights about Proximity Graph algorithms for Vector Search with Filtering!
Read more about ACORN here! - arxiv.org/pdf/2403.04871
Chapters
0:00 Welcome Liana and Abdel
0:40 What lead you to Approxiomate Nearest Neighbor Search?
2:05 What lead you to Filtered Vector Search?
3:50 ACORN, an overview
10:35 How to connect disparate regions?
12:40 Two-Hop Neighborhood Heuristic
20:48 ACORN and Pre-Filtering
22:30 Strengthening a Predicate Subgraph
24:26 Hyperparameter Recommendations
27:28 Time Complexity Analysis of ACORN
29:45 Importance of the Hierarchy in ACORN
33:30 Selective Pruning
38:05 Experimental Analysis and Vector / Filter Correlation
47:34 Observability for Vector Databases
49:45 Compound AI Systems
