search

HKUDS / MMSSL

[WWW'2023] "MMSSL: Multi-Modal Self-Supervised Learning for Recommendation"
https://arxiv.org/abs/2302.10632
155 stars 20 forks source link

Some questions about your `Multi-Modal High-Order Connectivity` module. #11

Closed liuxianyi closed 1 year ago

liuxianyi commented 1 year ago

An excellent paper, but I was confused by your module Multi-Modal High-Order Connectivity: 截屏2023-06-05 17 38 50 In this formula, If I have deduced correctly, $\hat{E}_u^l$ is from the output of modality-wise Dependency Modeling. Its dimension is $m \times d$, supposing that $m$ is the nums of users. The $A \in \mathbb{R}^{n \times m}$ is the user-inter interactive matrix, and $n$ denotes the item nums. From those, it is inferred that the dimension of the output representations $\hat{E}_u^{l+1}$ is $n \times d$, which is corresponding to the representations of items but users. So, Can help me solve my confusion？ thanks.

weiwei1206 commented 1 year ago

Thank you for your interest in our work~

Based on your feedback, the draft has been updated, and the revised version will soon be available on arXiv. We sincerely appreciate your support and feedback.