def __init__(self, n_features=None, n_dim=8, lossfun=F.mean_squared_error,
lambda0=1, lambda1=1, lambda2=1, init_bias_mu=0.0,
init_bias_lv=0.0, intx_term=True, total_nobs=1):
self.n_dim = n_dim
self.n_features = n_features
self.lossfun = lossfun
self.lambda0 = lambda0
self.lambda1 = lambda1
self.lambda2 = lambda2
self.intx_term = intx_term
self.total_nobs = total_nobs
# In contrast to the FM model, the slopes and latent vectors
# will have means (mu) and log variances (lv) for each component.
super(VFM, self).__init__(bias_mu=L.Bias(shape=(1,)),
bias_lv=L.Bias(shape=(1,)),
slop_mu=L.Bias(shape=(1, 1)),
slop_lv=L.Bias(shape=(1, 1)),
slop_delta_mu=L.EmbedID(n_features, 1,
ignore_label=-1),
slop_delta_lv=L.EmbedID(n_features, 1,
ignore_label=-1),
feat_mu_vec=L.Bias(shape=(1, 1, n_dim)),
feat_lv_vec=L.Bias(shape=(1, 1, n_dim)),
feat_delta_mu=L.EmbedID(n_features, n_dim,
ignore_label=-1),
feat_delta_lv=L.EmbedID(n_features, n_dim,
ignore_label=-1))
# Xavier initialize weights
c = np.sqrt(n_features * n_dim) * 1e3
d = np.sqrt(n_features) * 1e3
self.feat_delta_mu.W.data[...] = np.random.randn(n_features, n_dim) / c
self.feat_delta_lv.W.data[...] = np.random.randn(n_features, n_dim) / c
self.slop_delta_mu.W.data[...] = np.random.randn(n_features, 1) / d
self.slop_delta_lv.W.data[...] = np.random.randn(n_features, 1) / d
self.bias_mu.b.data[...] *= 0.0
self.bias_mu.b.data[...] += init_bias_mu
self.bias_lv.b.data[...] *= 0.0
self.bias_lv.b.data[...] += init_bias_lv
评论列表
文章目录
