Research map / Label-efficient and robust learning / Recognition and long-tail
Fusing Social Networks with Deep Learning for Volunteerism Tendency Prediction
Yongpo Jia, Xuemeng Song, Jingbo Zhou, Li Liu, Liqiang Nie, David Rosenblum
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 source confidence weights (alpha) to deep fusion with consistency (ablation) | FARSEEING-na · Volunteerism prediction (10-fold CV) | F1-score: 87.867 -> 89.921 | Improved |
| add source consistency regularization with confidence (ablation) | FARSEEING-nw · Volunteerism prediction (10-fold CV) | F1-score: 89.101 -> 89.921 | Improved |
| add source consistency regularization without confidence (ablation) | FARSEEING-no · Volunteerism prediction (10-fold CV) | F1-score: 87.675 -> 87.867 | Improved |
| add source confidence regularization without consistency (ablation) | FARSEEING-no · Volunteerism prediction (10-fold CV) | F1-score: 87.675 -> 89.101 | Improved |
| fuse deep per-source networks vs linear MSNL | MSNL · Volunteerism prediction (10-fold CV) | F1-score: 86.641 -> 89.921 | Improved |
| use per-source weighted fusion vs concatenating sources in DBN | DBN · Volunteerism prediction (10-fold CV) | F1-score: 86.635 -> 89.921 | Improved |
| add Facebook and LinkedIn to Twitter alone (ablation) | FARSEEING · Volunteerism prediction (10-fold CV) | F1-score: 83.395 -> 89.921 | Improved |
| use four or more hidden layers instead of three (ablation) | FARSEEING · Volunteerism prediction (10-fold CV) | F1-score | No clear effect |
| use user topic vs demographic features (ablation) | FARSEEING · Volunteerism prediction (10-fold CV) | F1-score: 76.661 -> 86.690 | Improved |
Closest papers by meaning
- Disentangled Modeling of Preferences and Social Influence for Group Recommendation (AAAI 2025 · similarity 0.82)
- Networked Inequality: Preferential Attachment Bias in Graph Neural Network Link Prediction (ICML 2024 · similarity 0.81)
- Adversarial Socialbots Modeling Based on Structural Information Principles (AAAI 2024 · similarity 0.81)
- Theoretical and Empirical Insights into the Origins of Degree Bias in Graph Neural Networks (NeurIPS 2024 · similarity 0.81)
- Non-Euclidean Mixture Model for Social Network Embedding (NeurIPS 2024 · similarity 0.81)
- Link Prediction in Multilayer Networks via Cross-Network Embedding (AAAI 2024 · similarity 0.81)
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.
