Node Embedding using Mutual Information and Self-Supervision based\n Bi-level Aggregation
Bibliographic record
Abstract
Graph Neural Networks (GNNs) learn low dimensional representations of nodes\nby aggregating information from their neighborhood in graphs. However,\ntraditional GNNs suffer from two fundamental shortcomings due to their local\n($l$-hop neighborhood) aggregation scheme. First, not all nodes in the\nneighborhood carry relevant information for the target node. Since GNNs do not\nexclude noisy nodes in their neighborhood, irrelevant information gets\naggregated, which reduces the quality of the representation. Second,\ntraditional GNNs also fail to capture long-range non-local dependencies between\nnodes. To address these limitations, we exploit mutual information (MI) to\ndefine two types of neighborhood, 1) \\textit{Local Neighborhood} where nodes\nare densely connected within a community and each node would share higher MI\nwith its neighbors, and 2) \\textit{Non-Local Neighborhood} where MI-based node\nclustering is introduced to assemble informative but graphically distant nodes\nin the same cluster. To generate node presentations, we combine the embeddings\ngenerated by bi-level aggregation - local aggregation to aggregate features\nfrom local neighborhoods to avoid noisy information and non-local aggregation\nto aggregate features from non-local neighborhoods. Furthermore, we leverage\nself-supervision learning to estimate MI with few labeled data. Finally, we\nshow that our model significantly outperforms the state-of-the-art methods in a\nwide range of assortative and disassortative graphs.\n
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.003 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 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".