Fix infinite loop in _neg_sample when item_set covers all items#2210
Open
he-yufeng wants to merge 1 commit intoRUCAIBox:masterfrom
Open
Fix infinite loop in _neg_sample when item_set covers all items#2210he-yufeng wants to merge 1 commit intoRUCAIBox:masterfrom
he-yufeng wants to merge 1 commit intoRUCAIBox:masterfrom
Conversation
When a user's interaction sequence contains all possible item IDs (1 to n_items-1), the while loop in _neg_sample could never terminate because no valid negative sample exists. This adds a guard check before the loop and returns 0 (padding index) as a fallback. Also converts item_set to a set for O(1) membership lookups. Fixes RUCAIBox#2193 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
_neg_sampleinMaskItemSequenceenters an infinite loop when a user's interaction history covers all possible item IDs (1 ton_items - 1)item_setto asetfor O(1) membership lookupsRoot Cause
When
MAX_ITEM_LIST_LENGTHexceeds the number of unique items in the dataset (e.g., 100 vs 10 items), a user's masked sequence can contain all valid item IDs. Thewhile item in item_setloop then never terminates.Test plan
🤖 Generated with Claude Code