RippleNet
RippleNet copied to clipboard
hwwang55
A tensorflow implementation of RippleNet
`self.transform_matrix = nn.Linear(self.dim, self.dim, bias=False) item_embeddings = self._update_item_embedding(item_embeddings, o) item_embeddings = self.transform_matrix(item_embeddings + o) ` As the codes above show, vector o can be seen as the 1-order response of...
Hi, I have used RippleNet on my dataset but can't get the explainability by tracking the paths to the item with high relevance probability in the KG. So I try...
王教授，您好，我已经按照readme的步骤跑了preprocess.py和main.py，但RippleNet的输出是预测点击的概率值，请问概率值怎么输出的呢。如果我没了解全面，在此感到抱歉，还请您解答一下我的困惑。十分感谢
王教授您好，我想请问kg_rehashed.txt的第二列关系为什么是三个组合，例如2474 film.writer.film 2475是表示什么呢？
Professor @hwwang55 thank you for your work and for providing us the code for RippleNet. RippleNet as far as i'm concerned does not take into consideration the timing and the...
王教授您好，冒昧的打扰您，想问您一下一些数据的具体含义。以movie数据为例，data文件夹中，ratings.dat是原始评分数据，给出了6040位用户对3952部电影的评分；item_index2entity_id_rehashed.txt是对其中2347部电影的重新编号；那么kg_part1_rehashed.txt和kg_part2_rehashed.txt文件中，第一列数据代表什么含义呢？我看这两个文件第一列中，存在超过电影数目的数字，而对应的relation中是以film开头，有些想不明白，想了解一下第一列数据的具体含义。感谢并期待您的回复。
论文里公式13第二部分主要这样的：Ir - EtRE 代码里似乎对应(因为论文里kge损失的权重λ2和代码里kge_weight的默认值都是0.01) ``` self.kge_loss = 0 for hop in range(self.n_hop): h_expanded = tf.expand_dims(self.h_emb_list[hop], axis=2) t_expanded = tf.expand_dims(self.t_emb_list[hop], axis=3) hRt = tf.squeeze(tf.matmul(tf.matmul(h_expanded, self.r_emb_list[hop]), t_expanded)) self.kge_loss += tf.reduce_mean(tf.sigmoid(hRt)) self.kge_loss =...
`l2_loss` for transform matrix was never added to total `l2_loss`, as the values of constants are wrong in the if the condition.
