PDN 中的 PATH 分数计算与论文中的公式不符
- Dominant language
- Python
- Stars
- 2.4k
- Forks
- 383
- PR merge metrics
- No merged PRs in 30d
Description
https://github.com/alibaba/EasyRec/blob/d965fb796ca834285b82dec071128aec3a82c584/easy_rec/python/model/pdn.py#L43-L45
代码中实现的是:
```
trigger_out = tf.exp()
sim_out = tf.exp()
logits = tf.multiplay(sim_out, trigger_out)
```
相当于是:
$$ PATH_{uji} = e^{t_{uj}} e^{s_{ji}} $$
论文中的合并公式(公式(10))是:
$$
PATH_{uji} = MEG(t_{uj}, s_{ji}) = \ln(1 + e^{t_{uj}} e^{s_{ji}})
$$
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by reading easy_rec/python/model/pdn.py lines 43-45 and compare the calculation with formula (10) in the referenced paper. Look for existing PDN model tests or validation around this calculation; done means the PATH score follows the paper’s formula and the relevant behavior is validated.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, tensorflow
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Clearly specified
- Newbie friendliness
- 48/100