[VoVAllen]

Hi, I'm the author of the article. I actually think the opposite of what you mentioned. IVF is more suitable for prefiltering compared to HNSW. For prefiltering in HNSW, there is a certain requirement for the filtering rate—it can't be too low, or the entire graph may become disconnected. For instance, with the commonly used parameter m=16, each node can have at most 16 neighbors. If the filtering rate is below 5%, it can directly result in no neighbors meeting the condition, causing the algorithm to fail entirely. This is why the academic community has proposed alternatives like ACRON[1]. On the other hand, IVF doesn't have this problem at all—you can check whether a candidate meets the condition before calculating distances.

[1] https://arxiv.org/abs/2403.04871

[generall]

In IVF you can start checking conditions only in the final bucket. There are no guarantees if the bucket has any acceptable value, and there are no procedures to find the bucket which has acceptable values before scanning it.

[VoVAllen]

I'm not sure I fully understand your point. This can be implemented quite easily by organizing each posting list with specific attributes to locate the values efficiently. For example, you could build each posting list into a B-tree, or similar to a column-oriented format that stores attribute statistics to enable skip scanning. Could you elaborate more?

[generall]

In this scenario posting list have to share all the same attributes as each element inside the list.