我在 Edward 中编写了概率矩阵分解模型。我正在尝试将其移植到 TFP,但我不确定如何定义对数似然和 KL 散度项。这是爱德华的代码 -
# MODEL
U = Normal(
loc=0.0,
scale=1.0,
sample_shape=[n_latent_dims, batch_size])
V = Normal(
loc=0.0,
scale=1.0,
sample_shape=[n_latent_dims, n_features])
R = Bernoulli(logits=tf.matmul(tf.transpose(U), V))
R_ph = tf.placeholder(tf.int32, [None, n_features])
# INFERENCE
qU = Normal(
loc=tf.get_variable("qU/loc",
[n_latent_dims, batch_size]),
scale=tf.nn.softplus(
tf.get_variable("qU/scale",
[n_latent_dims, batch_size])))
qV = Normal(
loc=tf.get_variable("qV/loc",
[n_latent_dims, n_features]),
scale=tf.nn.softplus(
tf.get_variable("qV/scale",
[n_latent_dims, n_features])))
qR = Bernoulli(logits=tf.matmul(tf.transpose(qU), qV))
qR_avg = Bernoulli(
logits=tf.reduce_mean(qR.parameters['logits'], 0))
log_likli = tf.reduce_mean(qR_avg.log_prob(R_ph), 1)
inference = ed.KLqp(
{
U: qU,
V: qV
}, data={self.R: self.R_ph})
inference_init = inference.initialize()
init = tf.global_variables_initializer()