FEA: Add FiGNN in Context Aware models #1509
Merged
Conversation
This file contains 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
zhengbw0324
requested changes
Oct 25, 2022
| """ FiGNN is a novel CTR prediction model based on GGNN, | ||
| which can model sophisticated interactions among feature fields on the graph-structured features. | ||
| """ | ||
|
|
There was a problem hiding this comment.
这里要指明模型类型，如PAIRWISE或POINTWISE
There was a problem hiding this comment.
不是在文字里，是在代码里加一下input_type = InputType.PAIRWISE
| self.bias_p = nn.Parameter(torch.zeros(embedding_size)) | ||
|
|
||
| def forward(self, g, h): | ||
| h_out = torch.matmul(self.W_out, h.unsqueeze(-1)).squeeze(-1) |
There was a problem hiding this comment.
计算顺序尽量参考原论文公式，虽然这里应该是等价的。
| self.attention_size = config['attention_size'] | ||
| self.n_layers = config['n_layers'] | ||
| self.num_heads = config['num_heads'] | ||
| self.dropout_probs = config['dropout_probs'] |
There was a problem hiding this comment.
两个不同的dropout参数分开，增加可读性也方便调参。
| self.gru_cell = nn.GRUCell(self.attention_size, self.attention_size) | ||
| # Attentional Scoring Layer | ||
| self.mlp1 = nn.Linear(self.attention_size, 1, bias=False) | ||
| self.mlp2 = nn.Sequential( |
There was a problem hiding this comment.
这里套一层nn.Sequential是多余的
| nn.Linear(self.num_feature_field * self.attention_size, self.num_feature_field, bias=False) | ||
| ) | ||
| self.sigmoid = nn.Sigmoid() | ||
| self.loss = nn.BCELoss() |
There was a problem hiding this comment.
建议使用nn.BCEWithLogitsLoss()，可以参考一下其他context模型
AoiDragon
reviewed
Oct 26, 2022
CIEEMio
requested review from
AoiDragon and
zhengbw0324
and removed request for
AoiDragon
zhengbw0324
requested changes
Nov 6, 2022
| """ FiGNN is a novel CTR prediction model based on GGNN, | ||
| which can model sophisticated interactions among feature fields on the graph-structured features. | ||
| """ | ||
|
|
There was a problem hiding this comment.
不是在文字里，是在代码里加一下input_type = InputType.PAIRWISE
AoiDragon
approved these changes
Nov 11, 2022
zhengbw0324
approved these changes
Nov 11, 2022
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
No description provided.