Research map / Graph learning / Knowledge and temporal graphs
Social Influence Does Matter: User Action Prediction for In-Feed Advertising
Hongyang Wang, Qingfei Meng, Ju Fan, Yuchen Li, Laizhong Cui, Xiaoman Zhao, Chong Peng, Gong Chen, Xiaoyong Du
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add learned social influence features (WL+GAT) to LR | LR · WechatDay | AUC (%): 80.0 -> 83.1 | Improved |
| add social influence features to ResFM | ResFM · WechatWeek | AUC (%): 81.0 -> 84.4 | Improved |
| add social influence features to ResFM | ResFM · Weibo | AUC (%): 82.0 -> 84.8 | Improved |
| add social influence features to LR | LR · Weibo | AUC (%): 75.0 -> 79.0 | Improved |
| use proposed framework instead of DeepInf | WechatDay · WechatDay | AUC (%): 69.4 -> 84.4 | Improved |
| use WL-based structure encoding instead of Node2vec (ablation) | influence structure · advertising datasets | AUC (%) | Improved |
| use WLEmb instead of WLFrq encoding (ablation) | LR · advertising datasets | AUC (%) | Mixed |
| combine WL encoding with GAT (WL+GAT) vs GCN/GAT alone (ablation) | influence learning · all datasets | AUC (%) | Improved |
| increase WL graph encoding dimension (ablation) | WL encoding · WechatDay | AUC (%) | Mixed |
Closest papers by meaning
- DiffIM: Differentiable Influence Minimization with Surrogate Modeling and Continuous Relaxation (AAAI 2025 · similarity 0.84)
- Disentangled Modeling of Preferences and Social Influence for Group Recommendation (AAAI 2025 · similarity 0.83)
- Multi-Label Node Classification with Label Influence Propagation (ICLR 2025 · similarity 0.82)
- Motif-oriented influence maximization for viral marketing in large-scale social networks (NeurIPS 2024 · similarity 0.82)
- Graph Bayesian Optimization for Multiplex Influence Maximization (AAAI 2024 · similarity 0.82)
- TSGAN: Temporal Social Graph Attention Network for Aggressive Behavior Forecasting (AAAI 2025 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
