文章

GenRec综述论文笔记

GenRec综述论文笔记

论文链接:https://arxiv.org/abs/2409.15173

book structure

GenRec综述论文笔记 配图 1

Advantages of recommender systems with generative models

GenRec综述论文笔记 配图 2

Outline of key techniques and publications in LLM-driven RSs

GenRec综述论文笔记 配图 3

Chap4-LLM Rec

4.3 Encoder-only LLM Rec

encoder-only LLMs can be used in two main architectures: as dense retrievers (c.f. Sec 4.3.1) or as cross-encoders (c.f. Sec 4.3.2).

GenRec综述论文笔记 配图 4

Autoregressive LLM inputs are called prompts, which are sequences of tokens expressing a task such as top-k recommendation, rating prediction, or explanation generation.

GenRec综述论文笔记 配图 5

4.5 Retrieval Augmented Rec

GenRec综述论文笔记 配图 6

4.6 LLMs Representation Generation

GenRec综述论文笔记 配图 7

4.7 Conversational Rec

GenRec综述论文笔记 配图 8

Chap5-Multi-modal GMs for Rec

5.1 Introduction

Why?——item cold start problem, user request understanding, complex recsys scenes(virtual try-on, conversational shopping assistans)

Challenges——alignment,latent space learning

5.2 Contrastive Multimodal Rec

CLIP

GenRec综述论文笔记 配图 9

Align BEfore Fuse (ALBEF)

GenRec综述论文笔记 配图 10

5.3 Generative Multimodal Rec

GAN

GenRec综述论文笔记 配图 11

VAE

GenRec综述论文笔记 配图 12

Diffusion

GenRec综述论文笔记 配图 13

5.4 Applications of Multimodal Rec

  • E-commerce

  • product visualization-virtual try on

  • Marketing-create personalized ad images and videos

  • Streaming services-Long and short-form video,music,audiobooks,podcasts,radio

  • Travel

本文由作者按照 CC BY 4.0 进行授权