'Include multiple features in bert4rec or similar transformer for recommendation systems

I have a dataset where I have items, users and list of items that each user likes. Now I would like to suggest a news items to the users.

I would like to use bert4rec or similar model but as I see bert4rec does not care about the the features of the items. All items for it are like a black box with ID. Can u suggest me what can I do if I want to create smarter model which cares about the attributes of the items (color, size, type...) and so on?

bert-language-modelrecommender-systems


Sources

This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.

Source: Stack Overflow

Solution Source

Related Questions

why do pooler use tanh as a activation func in bert, rather than gelu?

Does Fine-tunning Bert Model in multiple times with different dataset make it more accuracy?

huggingface transformers convert logit scores to probability

Why does BERT Model fail to find an option that matches my input positional arguments?

How to apply max_length to truncate the token sequence from the left in a HuggingFace tokenizer?

Pretraining a language model on a small custom corpus

what's the difference between "self-attention mechanism" and "full-connection" layer?

Target Data Missing from tensorflow fit()

Bert embedding layer raises 'ValueError: A target array with shape ' with BiLSTM in keras tensorflow

ReadError: file could not be opened successfully. But I am not sure where the tar file is stored to resolve this

Continual pre-training vs. Fine-tuning a language model with MLM

Early stopping in Bert Trainer instances

how to train a bert model from scratch with huggingface?

transformers and BERT downloading to your local machine

How to specify a proxy in transformers pipeline