The code seems not to be the same as in the paper

[keyboardpianist]

In preprocess.py it generates context pairs during 1 to T, and the model learned from 1 to T to predict link in time T?

def get_context_pairs(graphs, num_time_steps):
    """ Load/generate context pairs for each snapshot through random walk sampling."""
    load_path = "data/{}/train_pairs_n2v_{}.pkl".format(FLAGS.dataset, str(num_time_steps - 2))
    try:
        context_pairs_train = dill.load(open(load_path, 'rb'))
        print("Loaded context pairs from pkl file directly")
    except (IOError, EOFError):
        print("Computing training pairs ...")
        context_pairs_train = []
        for i in range(0, num_time_steps):
            context_pairs_train.append(run_random_walks_n2v(graphs[i], graphs[i].nodes()))
        dill.dump(context_pairs_train, open(load_path, 'wb'))
        print ("Saved pairs")

    return context_pairs_train

maybe for i in range(0, num_time_steps - 1):?

[zhaohaixiangbobo]

in the mian function ，it replace the graph[-1] edge with graph[-2] edge

[trytodoit227]

hello, do you know how to generate negative samples in models.py