# Coarse-to-Fine Lightweight Meta-Embedding for ID-Based Recommendation

arXiv: https://arxiv.org/abs/2501.11870 · HTML: https://mlsanity.com/paper/2501.11870/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 21 references that are in the map.
- First posted on arXiv 21 Jan 2025.

## Builds on (most cited first, 16 of 16)

- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering](https://mlsanity.com/paper/1602.01585/) (2016)
- [Compositional Embeddings Using Complementary Partitions for Memory-Efficient Recommendation Systems](https://mlsanity.com/paper/1909.02107/) (2019)
- [Learning to Embed Categorical Features without Embedding Tables for Recommendation](https://mlsanity.com/paper/2010.10784/) (2020)
- [Try This Instead: Personalized and Interpretable Substitute Recommendation](https://mlsanity.com/paper/2005.09344/) (2020)
- [Model Size Reduction Using Frequency Based Double Hashing for Recommender Systems](https://mlsanity.com/paper/2007.14523/) (2020)
- [On-Device Next-Item Recommendation with Self-Supervised Knowledge Distillation](https://mlsanity.com/paper/2204.11091/) (2022)
- [Learning Elastic Embeddings for Customizing On-Device Recommenders](https://mlsanity.com/paper/2106.02223/) (2021)
- [OptEmbed: Learning Optimal Embedding Table for Click-through Rate Prediction](https://mlsanity.com/paper/2208.04482/) (2022)
- [Delving Globally into Texture and Structure for Image Inpainting](https://mlsanity.com/paper/2209.08217/) (2022)
- [Diffusion-Based Cloud-Edge-Device Collaborative Learning for Next POI Recommendations](https://mlsanity.com/paper/2405.13811/) (2024)
- [Thinking inside The Box: Learning Hypercube Representations for Group Recommendation](https://mlsanity.com/paper/2204.02592/) (2022)
- [Efficient On-Device Session-Based Recommendation](https://mlsanity.com/paper/2209.13422/) (2022)
- [Continuous Input Embedding Size Search For Recommender Systems](https://mlsanity.com/paper/2304.03501/) (2023)
- [Nimble GNN Embedding with Tensor-Train Decomposition](https://mlsanity.com/paper/2206.10581/) (2022)

## Abstract (arXiv)

The state-of-the-art recommendation systems have shifted the attention to efficient recommendation, e.g., on-device recommendation, under memory constraints. To this end, the existing methods either focused on the lightweight embeddings for both users and items, or involved on-device systems enjoying the compact embeddings to enhance reusability and reduces space complexity. However, they focus solely on the coarse granularity of embedding, while overlook the fine-grained semantic nuances, to adversarially downgrade the efficacy of meta-embeddings in capturing the intricate relationship over both user and item, consequently resulting into the suboptimal recommendations. In this paper, we aim to study how the meta-embedding can efficiently learn varied grained semantics, together with how the fine-grained meta-embedding can strengthen the representation of coarse-grained meta-embedding. To answer these questions, we develop a novel graph neural networks (GNNs) based recommender where each user and item serves as the node, linked directly to coarse-grained virtual nodes and indirectly to fine-grained virtual nodes, ensuring different grained semantic learning, while disclosing: 1) In contrast to coarse-grained semantics, fine-grained semantics are well captured through sparse meta-embeddings, which adaptively 2) balance the embedding uniqueness and memory constraint. Additionally, the initialization method come up upon SparsePCA, along with a soft thresholding activation function to render the sparseness of the meta-embeddings. We propose a weight bridging update strategy that focuses on matching each coarse-grained meta-embedding with several fine-grained meta-embeddings based on the users/items' semantics. Extensive experiments substantiate our method's superiority over existing baselines. Our code is available at https://github.com/htyjers/C2F-MetaEmbed.