Link Prediction in Social Graphs using Representation Learning via Knowledge-Graph Embeddings and ConvNet (RLVECN)
Bibliographic record
Abstract
In recent times, Social Network Analysis (SNA) has become a very important and interesting subject matter with regard to Artificial Intelligence (AI) in that a vast variety of processes, comprising animate and inanimate entities, can be examined by means of SNA. As a result, prediction tasks within social network structures have become significant research problems in SNA. Hidden facts and details about social network structures can be effectively and efficiently harnessed for training AI models with the goal of predicting missing links/ties within a given social network. Thus, important factors such as the individual attributes of spatial social actors, and the underlying patterns of relationship binding these social actors must be taken into consideration because these factors are relevant in understanding the nature and dynamics of a given social network structure. In this paper, we have proposed an interesting hybrid model: Representation Learning via Knowledge-Graph Embeddings and ConvNet (RLVECN). Our proposition herein is designed for examining, extracting, and learning meaningful facts for resolving link prediction problems about social network structures. RLVECN utilizes an edge sampling approach for exploiting the representations of a social graph, via learning the context of each actor with respect to its neighboring actors, with the goal of generating vector-space embeddings per actor which are further harnessed for innate representations via a Convolutional Neural Network (ConvNet) sublayer. Successively, these relatively low-dimensional representations are fed as input features to a downstream classifier for solving link prediction problems in a given social network. Our proposition, RLVECN, has been trained and evaluated on six (6) real-world benchmark social graph datasets.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".