Influence maximization in social networks using role-based embedding
Bibliographic record
Abstract
Influence maximization (IM), a central issue in optimizing information diffusion on social platforms, aims to spread posts or comments more widely, rapidly, and efficiently. Existing studies primarily focus on the positive effects of incorporating heuristic calculations in IM approaches. However, heuristic models fail to consider the potential enhancements that can be achieved through network representation learning techniques. Some recent work is keen to use representation learning to deal with IM issues. However, few in-depth studies have explored the existing challenges in IM representation learning, specifically regarding the role characteristics and role representations. This paper highlights the potential advantages of combining heuristic computing and role embedding to solve IM problems. First, the method introduces role granularity classification to effectively categorize users into three distinct roles: opinion leaders, structural holes and normal nodes. This classification enables a deeper understanding of the dynamics of users within the network. Second, a novel role-based network embedding (RbNE) algorithm is proposed. By leveraging the concept of node roles, RbNE captures the similarity between nodes, allowing for a more accurate representation of the network structure. Finally, a superior IM approach, named RbneIM, is recommended. RbneIM combines heuristic computing and role embedding to establish a fusion-enhanced IM solution, resulting in an improved influence analysis process. Exploratory outcomes on six social network datasets indicate that the proposed approach outperforms state-of-the-art seeding algorithms in terms of maximizing influence. This finding highlights the effectiveness and efficacy of the proposed method in achieving higher levels of influence within social networks. The code is available at https://github.com/baiyazi/IM2 .
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.003 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".