IDvs.MoRec

IDvs.MoRec copied to clipboard

测试时为啥候选物品的embedding 不需要过Model模块的fc呢，也即MLP模块，而是直接使用物品的modalembedding或者说id embedding

2

self.fc = MLP_Layers(word_embedding_dim=num_fc_ftr, item_embedding_dim=args.embedding_dim, layers=[args.embedding_dim] * (args.dnn_layer + 1), drop_rate=args.drop_rate)这段代码在训练是对输入的embedding进行了转换，然后再与候选的正负样本计算相似度以及BCE损失， 在模型预测时，为啥是直接使用item_embeddings而不需要经过上面得MLP_Layers呢？ item_embeddings = item_embeddings.to(local_rank) with torch.no_grad(): eval_all_user = [] item_rank = torch.Tensor(np.arange(item_num) + 1).to(local_rank) for data in eval_dl: user_ids, input_embs,...

Jackie-gj

Hyperparameter about best performance.

2

I am intrigued by your work and have a few questions to discuss with you. You conducted hyperparameter search for IDRec and MoRec, could you provide the optimal hyperparameters that...

anonymous-st4rec

可否提供训练好的模型文件

1

jackaihfia2334

About In-batch debiased cross-entropy loss

2

Which article proposed In-batch debiased cross-entropy loss? Can you provide relevant literature?

wkml

Where is the DSSM code

2

Firstly, thanks for your insightful job. I am wondering where is the training code of DSSM?

anthony123

Fine-tuning Script

1

Thanks for sharing this interesting work. I was wondering if you are going to share the scripts for fine-tuning LLMs.

BoPeng112