MISS: Multi-Interest Self-Supervised Learning Framework for Click-Through Rate Prediction
Wei Guo, Can Zhang, Zhicheng He, Jiarui Qin, Huifeng Guo, Bo Chen, Ruiming Tang, Xiuqiang He, Rui Zhang
Abstract
CTR prediction is essential for modern recommender systems. Ranging from early factorization machines to deep learning based models in recent years, existing CTR methods focus on capturing useful feature interactions or mining important behavior patterns. Despite the effectiveness, we argue that these methods suffer from the risk of label sparsity (i.e., the user-item interactions are highly sparse with respect to the feature space), label noise (i.e., the collected user-item interactions are usually noisy), and the underuse of domain knowledge (i.e., the pairwise correlations between samples). To address these challenging problems, we propose a novel Multi-Interest Self-Supervised learning (MISS) framework which enhances the feature embeddings with interest-level self-supervision signals. With the help of two novel CNN-based multi-interest extractors, self-supervision signals are discovered with full considerations of different interest representations (point-wise and union-wise), interest dependencies (short-range and long-range), and interest correlations (inter-item and intra-item). Based on that, contrastive learning losses are further applied to the augmented views of interest representations, which effectively improves the feature representation learning. Furthermore, our proposed MISS frame-work can be used as an “plug-in” component with existing CTR prediction models and further boost their performances. Extensive experiments on three large-scale datasets show that MISS significantly outperforms the state-of-the-art models, by up to 13.55% in AUC, and also enjoys good compatibility with representative deep CTR models.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
5 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- MAP: A Model-agnostic Pretraining Framework for Click-through Rate Prediction cites A Simple Framework for Contrastive Learning of Visual Representations
- MAP: A Model-agnostic Pretraining Framework for Click-through Rate Prediction cites Big Self-Supervised Models are Strong Semi-Supervised Learners
- Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere cites A Simple Framework for Contrastive Learning of Visual Representations
- Self-supervised Graph Learning for Recommendation cites ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
- Self-supervised Graph Learning for Recommendation cites A Simple Framework for Contrastive Learning of Visual Representations
- AT4CTR: Auxiliary Match Tasks for Enhancing Click-Through Rate Prediction cites MAP: A Model-agnostic Pretraining Framework for Click-through Rate Prediction
- AT4CTR: Auxiliary Match Tasks for Enhancing Click-Through Rate Prediction cites A Simple Framework for Contrastive Learning of Visual Representations
- Big Self-Supervised Models are Strong Semi-Supervised Learners cites A Simple Framework for Contrastive Learning of Visual Representations
Cited by top-tier papers5
- MAP: A Model-agnostic Pretraining Framework for Click-through Rate PredictionJianghao Lin, Yanru Qu, Wei Guo, Xinyi Dai et al.KDD 2023 · 28 citations
- AT4CTR: Auxiliary Match Tasks for Enhancing Click-Through Rate PredictionQi Liu, Xuyang Hou, Defu Lian, Zhe Wang et al.AAAI 2024 · 11 citations
- All-in-One: Heterogeneous Interaction Modeling for Cold-Start Rating PredictionShuheng Fang, Kangfei Zhao, Yu Rong, Jeffrey Xu Yu et al.ICDE 2025 · 2 citations
- Personalized Multi-Interest Modeling for Cross-Domain Recommendation to Cold-Start UsersXiaodong Li, Jiawei Sheng, Jiangxia Cao, Xinghua Zhang et al.ICDE 2025 · 1 citation
- Revisiting Feature Interactions from the Perspective of Quadratic Neural Networks for Click-through Rate PredictionHonghao Li, Yiwen Zhang, Yi Zhang, Lei Sang et al.KDD 2025 · 1 citation
Builds on13
- A Simple Framework for Contrastive Learning of Visual RepresentationsTing Chen, Simon Kornblith, Mohammad Norouzi, Geoffrey E. HintonICML 2020 · 24,064 citations
- ALBERT: A Lite BERT for Self-supervised Learning of Language RepresentationsZhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel et al.ICLR 2020 · 7,418 citations
- Big Self-Supervised Models are Strong Semi-Supervised LearnersTing Chen, Simon Kornblith, Kevin Swersky, Mohammad Norouzi et al.NeurIPS 2020 · 2,611 citations
- Understanding Contrastive Representation Learning through Alignment and Uniformity on the HypersphereTongzhou Wang, Phillip IsolaICML 2020 · 2,360 citations
- Self-supervised Graph Learning for RecommendationJiancan Wu, Xiang Wang, Fuli Feng, Xiangnan He et al.SIGIR 2021 · 1,476 citations
Related papers
- Contrastive Learning for Sequential RecommendationXu Xie, Fei Sun, Zhaoyang Liu, Shiwen Wu et al.ICDE 2022 · 674 citations
- Dual Graph enhanced Embedding Neural Network for CTR PredictionWei Guo, Rong Su, Renhao Tan, Huifeng Guo et al.KDD 2021 · 72 citations
- Deep Match to Rank Model for Personalized Click-Through Rate PredictionZequn Lyu, Yu Dong, Chengfu Huo, Weijun RenAAAI 2020 · 73 citations
- Multi-Modal Self-Supervised Learning for RecommendationWei Wei, Chao Huang, Lianghao Xia, Chuxu ZhangWWW 2023 · 256 citations
- Disentangling Long and Short-Term Interests for RecommendationYu Zheng, Chen Gao, Jianxin Chang, Yanan Niu et al.WWW 2022 · 128 citations
