Learning Effective Embeddings for Dynamic Graphs and Quantifying Graph Embedding Interpretability
Bibliographic record
Abstract
Graph representation learning has been a very active research area in recent years. The goal of graph representation learning is to generate representation vectors that accurately capture the structure and features of large graphs. This is especially important because the quality of the graph representation vectors will affect the performance of these vectors in downstream tasks such as node classification and link prediction. Many techniques have been proposed for generating effective graph representation vectors. These methods can be applied to both static and dynamic graphs. A static graph is a single fixed graph, while a dynamic graph evolves over time, and its nodes and edges can be added or deleted from the graph. We surveyed the graph embedding methods for both static and dynamic graphs. The majority of the existing graph embedding methods are developed for static graphs. Therefore, since most real-world graphs are dynamic, developing novel graph embedding methods suitable for evolving graphs is essential. \nThis dissertation proposes three dynamic graph embedding models. In previous dynamic methods, the inputs were mainly adjacency matrices of graphs which are not memory efficient and may not capture the neighbourhood structure in graphs effectively. Therefore, we developed Dynnode2vec based on random walks using the static model Node2vec. Dynnode2vec generates node embeddings in each snapshot by initializing the current model with previous embedding vectors and training the model using a set of random walks obtained for nodes in the snapshot. Our second model, LSTM-Node2vec, is also based on random walks. This method leverages the LSTM model to capture the long-range dependencies between nodes in combination with Node2vec to generate node embeddings. Finally, inspired by the importance of substructures in the graphs, our third model TGR-Clique generates node embeddings by considering the effects of neighbours of a node in the maximal cliques containing the node. Experiments on real-world datasets demonstrate the effectiveness of our proposed methods in comparison to the state-of-the-art models. In addition, motivated by the lack of proper measures for quantifying and comparing graph embeddings interpretability, we proposed two interpretability measures for graph embeddings using the centrality properties of graphs.
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 | 0.014 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.007 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".