# Learning Graph Meta Embeddings for Cold-Start Ads in Click-Through Rate Prediction

arXiv: https://arxiv.org/abs/2105.08909 · HTML: https://mlsanity.com/paper/2105.08909/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 60 references that are in the map.
- First posted on arXiv 19 May 2021.

## Builds on (most cited first, 30 of 31)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [Wide & Deep Learning for Recommender Systems](https://mlsanity.com/paper/1606.07792/) (2016)
- [DeepFM: A Factorization-Machine based Neural Network for CTR Prediction](https://mlsanity.com/paper/1703.04247/) (2017)
- [Deep Interest Network for Click-Through Rate Prediction](https://mlsanity.com/paper/1706.06978/) (2017)
- [Deep & Cross Network for Ad Click Predictions](https://mlsanity.com/paper/1708.05123/) (2017)
- [Deep Interest Evolution Network for Click-Through Rate Prediction](https://mlsanity.com/paper/1809.03672/) (2018)
- [AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks](https://mlsanity.com/paper/1810.11921/) (2018)
- [xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems](https://mlsanity.com/paper/1803.05170/) (2018)
- [Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Rate](https://mlsanity.com/paper/1804.07931/) (2018)
- [Product-based Neural Networks for User Response Prediction](https://mlsanity.com/paper/1611.00144/) (2016)
- [MeLU: Meta-Learned User Preference Estimator for Cold-Start Recommendation](https://mlsanity.com/paper/1908.00413/) (2019)
- [Incremental Few-Shot Object Detection](https://mlsanity.com/paper/2003.04668/) (2020)
- [Deep Learning over Multi-field Categorical Data: A Case Study on User Response Prediction](https://mlsanity.com/paper/1601.02376/) (2016)
- [Warm Up Cold-start Advertisements: Improving CTR Predictions via Learning to Learn ID Embeddings](https://mlsanity.com/paper/1904.11547/) (2019)
- [Field-weighted Factorization Machines for Click-Through Rate Prediction in Display Advertising](https://mlsanity.com/paper/1806.03514/) (2018)
- [Higher-Order Factorization Machines](https://mlsanity.com/paper/1607.07195/) (2016)
- [User Behavior Retrieval for Click-Through Rate Prediction](https://mlsanity.com/paper/2005.14171/) (2020)
- [MiNet: Mixed Interest Network for Cross-Domain Click-Through Rate Prediction](https://mlsanity.com/paper/2008.02974/) (2020)
- [InfiniteWalk: Deep Network Embeddings as Laplacian Embeddings with a Nonlinearity](https://mlsanity.com/paper/2006.00094/) (2020)
- [Meta Multi-Task Learning for Sequence Modeling](https://mlsanity.com/paper/1802.08969/) (2018)
- [Deep Spatio-Temporal Neural Networks for Click-Through Rate Prediction](https://mlsanity.com/paper/1906.03776/) (2019)
- [Dynamic Meta-Embeddings for Improved Sentence Representations](https://mlsanity.com/paper/1804.07983/) (2018)
- [Representation Learning-Assisted Click-Through Rate Prediction](https://mlsanity.com/paper/1906.04365/) (2019)
- [Lifelong Domain Word Embedding via Meta-Learning](https://mlsanity.com/paper/1805.09991/) (2018)
- [Click-Through Rate Prediction with the User Memory Network](https://mlsanity.com/paper/1907.04667/) (2019)

## Built on by (most cited first, 13 of 13)

- [Click-Through Rate Prediction in Online Advertising: A Literature Review](https://mlsanity.com/paper/2202.10462/) (2022)
- [Alleviating Cold-start Problem in CTR Prediction with A Variational Embedding Learning Framework](https://mlsanity.com/paper/2201.10980/) (2022)
- [LKPNR: LLM and KG for Personalized News Recommendation Framework](https://mlsanity.com/paper/2308.12028/) (2023)
- [Graph Neural Networks for Tabular Data Learning: A Survey with Taxonomy and Directions](https://mlsanity.com/paper/2401.02143/) (2024)
- [Click-through Rate Prediction with Auto-Quantized Contrastive Learning](https://mlsanity.com/paper/2109.13921/) (2021)
- [Personalizing Intervened Network for Long-tailed Sequential User Behavior Modeling](https://mlsanity.com/paper/2208.09130/) (2022)
- [Addressing Cold-start Problem in Click-Through Rate Prediction via Supervised Diffusion Modeling](https://mlsanity.com/paper/2504.06270/) (2025)
- [Robust Graph Meta-learning for Weakly-supervised Few-shot Node Classification](https://mlsanity.com/paper/2106.06873/) (2021)
- [LiMAML: Personalization of Deep Recommender Models via Meta Learning](https://mlsanity.com/paper/2403.00803/) (2024)
- [M^2VAE: Multi-Modal Multi-View Variational Autoencoder for Cold-start Item Recommendation](https://mlsanity.com/paper/2508.00452/) (2025)
- [Item Cold Start Recommendation via Adversarial Variational Auto-encoder Warm-up](https://mlsanity.com/paper/2302.14395/) (2023)
- [LLM-Empowered Representation Learning for Emerging Item Recommendation](https://mlsanity.com/paper/2512.10370/) (2025)
- [MDiffFR: Modality-Guided Diffusion Generation for Cold-start Items in Federated Recommendation](https://mlsanity.com/paper/2512.24715/) (2025)

## Abstract (arXiv)

Click-through rate (CTR) prediction is one of the most central tasks in online advertising systems. Recent deep learning-based models that exploit feature embedding and high-order data nonlinearity have shown dramatic successes in CTR prediction. However, these models work poorly on cold-start ads with new IDs, whose embeddings are not well learned yet. In this paper, we propose Graph Meta Embedding (GME) models that can rapidly learn how to generate desirable initial embeddings for new ad IDs based on graph neural networks and meta learning. Previous works address this problem from the new ad itself, but ignore possibly useful information contained in existing old ads. In contrast, GMEs simultaneously consider two information sources: the new ad and existing old ads. For the new ad, GMEs exploit its associated attributes. For existing old ads, GMEs first build a graph to connect them with new ads, and then adaptively distill useful information. We propose three specific GMEs from different perspectives to explore what kind of information to use and how to distill information. In particular, GME-P uses Pre-trained neighbor ID embeddings, GME-G uses Generated neighbor ID embeddings and GME-A uses neighbor Attributes. Experimental results on three real-world datasets show that GMEs can significantly improve the prediction performance in both cold-start (i.e., no training data is available) and warm-up (i.e., a small number of training samples are collected) scenarios over five major deep learning-based CTR prediction models. GMEs can be applied to conversion rate (CVR) prediction as well.