Research map / Probabilistic and scientific modeling / Variational and generative sampling
Estimation of a Low-rank Topic-Based Model for Information Cascades
Ming Yu, Varun Gupta, Mladen Kolar
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 |
|---|---|---|---|
| use the low-rank topic model (influence and receptivity matrices) instead of NetRate's single diffusion matrix | NetRate · MemeTracker test cascades | AIC (test): 5.08 x 10^5 -> 2.38 x 10^5 (vs TopicCascade); NetRate 2.60 x 10^5 -> 2.38 x 10^5 | Improved |
| use the low-rank topic model with 2pK parameters instead of full TopicCascade with p^2K parameters | TopicCascade · MemeTracker test cascades | number of parameters: 2500000 -> 10000 | Improved |
| use the low-rank model instead of TopicCascade | TopicCascade · MemeTracker test cascades | test negative log-likelihood: 81.8 -> 82.3 | No clear effect |
| use the low-rank model instead of NetRate and TopicCascade (train vs test gap) | NetRate / TopicCascade · MemeTracker | train negative log-likelihood: train 68.5 -> 80.3 vs test 81.1 -> 82.3 (NetRate); 62.5 vs 81.8 (TopicCascade) | Improved |
| use the low-rank model instead of TopicCascade at large scale (xi=8) | TopicCascade · synthetic running time | running time (s): 1310.7 -> 454.9 | Improved |
| use NetRate (ignores topics) instead of the proposed model | proposed model · synthetic running time | running time (s): 454.9 -> 211.0 (NetRate is faster) | Hurt |
| use g2 (l2 column norm) instead of g1 (l1) regularization at small sample size (ablation) | Algorithm 1 with g1 · synthetic, p=50 | estimation error | Hurt |
| use g2 (l2 column norm) instead of g1 regularization at large sample size (ablation) | Algorithm 1 with g1 · synthetic, p=50 | estimation error | Improved |
| reduce dimension to p=10, K=6 and increase sample size (ablation) | TopicCascade vs proposed model · synthetic small p | estimation error | Improved |
| use small p=10, K=6 (NetRate vs proposed model) | NetRate · synthetic small p | test negative log-likelihood | Mixed |
| use a larger regularization parameter (20 times the optimal) to improve F1 on network recovery | proposed model · synthetic p=50 | F1 score | Improved |
| use a denser graph (5-6 topics per row instead of 2-3) (ablation) | proposed model vs baselines · synthetic dense graph | negative log-likelihood and estimation error | No clear effect |
Closest papers by meaning
- Heterogeneous Diffusion Structure Inference for Network Cascade (NeurIPS 2025 · similarity 0.89)
- Estimating Diffusion Networks: Recovery Conditions, Sample Complexity and Soft-thresholding Algorithm (JMLR 2016 · similarity 0.87)
- MSR: A Multifaceted Self-Retrieval Framework for Microscopic Cascade Prediction (AAAI 2025 · similarity 0.86)
- The Irrelevance of Influencers: Information Diffusion with Re-Activation and Immunity Lasts Exponentially Long on Social Network Models (AAAI 2024 · similarity 0.85)
- A Thorough Comparison Between Independent Cascade and Susceptible-Infected-Recovered Models (AAAI 2025 · similarity 0.85)
- Enhancing Multi-Scale Diffusion Prediction via Sequential Hypergraphs and Adversarial Learning (AAAI 2024 · similarity 0.85)
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.
