请问您超参数用的是什么，建议您多跑几个epoch 调一下参数试试看，transe是个强基线效果不错的。

from openbg500.

您好！建议尝试一下https://github.com/OpenBGBenchmark/OpenBG-IMG/tree/main/TransE 中的参数设置。

from openbg500.

代码的参数设置是借鉴的OpenBG-IMG/tree/main/TransE 中的参数设置
`# dataloader for training
train_dataloader = TrainDataLoader(
in_path = data_path,
nbatches = 100,
threads = 8,
sampling_mode = "normal",
bern_flag = 1,
filter_flag = 1,
neg_ent = 25,
neg_rel = 0)

dataloader for test

test_dataloader = TestDataLoader(data_path, "link")

define the model

transe = TransE(
ent_tot = train_dataloader.get_ent_tot(),
rel_tot = train_dataloader.get_rel_tot(),
dim = 200,
p_norm = 1,
norm_flag = True)

define the loss function

model = NegativeSampling(
model = transe,
loss = MarginLoss(margin = 5.0),
batch_size = train_dataloader.get_batch_size()
)

train the model

trainer = Trainer(model = model, data_loader = train_dataloader, train_times = 1000, alpha = 1.0, use_gpu = True)
trainer.run()
transe.save_checkpoint('./checkpoints/openbg_500.ckpt')
`

最后跑出来的结果是这样的

`metric: MRR MR hit@10 hit@3 hit@1
l(raw): 0.000000 0.000000 0.000000 0.000000 0.000000
r(raw): 0.000018 131553.234375 0.000000 0.000000 0.000000
averaged(raw): 0.000009 65776.617188 0.000000 0.000000 0.000000

l(filter): 0.000000 0.000000 0.000000 0.000000 0.000000
r(filter): 0.000018 131553.234375 0.000000 0.000000 0.000000
averaged(filter): 0.000009 65776.617188 0.000000 0.000000 0.000000
type constraint results:
metric: MRR MR hit@10 hit@3 hit@1
l(raw): 0.000000 0.000000 0.000000 0.000000 0.000000
r(raw): 0.055832 479.256195 0.194600 0.044200 0.000000
averaged(raw): 0.027916 239.628098 0.097300 0.022100 0.000000

l(filter): 0.000000 0.000000 0.000000 0.000000 0.000000
r(filter): 0.055832 479.256195 0.194600 0.044200 0.000000
averaged(filter): 0.027916 239.628098 0.097300 0.022100 0.000000
MRR: 0.027916, MR: 239.628098, HITS@10: 0.097300, HITS@3: 0.022100, HITS@1: 0.000000
`

from openbg500.

你好，我尝试复现了一下，问题在于OpenKE中用于计算指标的文件是test文件，请你检查一下你的test文件是否包含完整的三元组。我们提供的OpenBG500数据集中所使用的test只包含头实体和关系，预测尾实体的过程需要像https://github.com/OpenBGBenchmark/OpenBG-IMG/tree/main/TransE 中一样，先把尾实体使用ent_000000来填充，然后再生成result文件，如果你遵循的是以上步骤，请你将result文件提交到阿里云天池OpenBG Benchmark中进行结果评测。如果你想在本地使用OpenKE取得正确的结果，请你使用以下数据集中的OpenBG500_answer.tsv文件来替代你的test文件进行模型评估，谢谢。
https://drive.google.com/file/d/1pD_icqV-lLbCXN2rfBaq-Y5i_XcKVCzM/view

from openbg500.

问题已经解决 感谢答疑！！

from openbg500.