Refactor BST transformer; bump PyTorch to 1.10 - #233
Merged
Conversation
Update README (EN/ZH) to require PyTorch 1.10+. Refactor BST model: add max_seq_len parameter and positional embeddings; compute fused item_dim from history features and validate it matches target_dim and is divisible by nhead. Change Transformer d_model to item_dim, use LeakyReLU activation, and build a TransformerEncoder with the new pos embedding. Fuse history features per timestep, append the target as the final token, construct a padding mask aggregated across history features, and use the transformer output at the target position as the interest representation. Adjust MLP input to include interest, flattened target embeddings, and other features; add sequence length checks and clearer validation errors.
github-actions
Bot
added
documentation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Pull Request / 拉取请求
What does this PR do? / 这个PR做了什么？
Update README (EN/ZH) to require PyTorch 1.10+. Refactor BST model: add max_seq_len parameter and positional embeddings; compute fused item_dim from history features and validate it matches target_dim and is divisible by nhead. Change Transformer d_model to item_dim, use LeakyReLU activation, and build a TransformerEncoder with the new pos embedding. Fuse history features per timestep, append the target as the final token, construct a padding mask aggregated across history features, and use the transformer output at the target position as the interest representation. Adjust MLP input to include interest, flattened target embeddings, and other features; add sequence length checks and clearer validation errors.
Type of Change / 变更类型