train.py 文件源码

def bpr_loss(x, dynamic_user, item_embedding, config):
    '''
        bayesian personalized ranking loss for implicit feedback
        parameters:
        - x: batch of users' baskets
        - dynamic_user: batch of users' dynamic representations
        - item_embedding: item_embedding matrix
        - config: model configuration
    '''
    nll = 0
    ub_seqs = []
    for u,du in zip(x, dynamic_user):
        du_p_product = torch.mm(du, item_embedding.t()) # shape: max_len, num_item
        nll_u = [] # nll for user
        for t, basket_t in enumerate(u):
            if basket_t[0] != 0 and t != 0:
                pos_idx = torch.cuda.LongTensor(basket_t) if config.cuda else torch.LongTensor(basket_t)
                # Sample negative products
                neg = [random.choice(range(1, config.num_product)) for _ in range(len(basket_t))] # replacement
                # neg = random.sample(range(1, config.num_product), len(basket_t)) # without replacement
                neg_idx = torch.cuda.LongTensor(neg) if config.cuda else torch.LongTensor(neg)
                # Score p(u, t, v > v')
                score = du_p_product[t - 1][pos_idx] - du_p_product[t - 1][neg_idx]
                #Average Negative log likelihood for basket_t
                nll_u.append(- torch.mean(torch.nn.LogSigmoid()(score)))
        nll += torch.mean(torch.cat(nll_u))
    return nll