Bibliographic record
Abstract
Graph Convolutional Networks (GCNs) are a powerful approach for learning graph representations and show promising results in various applications. Despite their success, they are usually limited to shallow architectures due to the vanishing gradients, over-smoothing, and over-squashing problems. As Convolutional Neural Networks benefit tremendously from stacking very deep layers, recently techniques such as various types of residual connections and dense connections are proposed to tackle these problems and make GCNs go deeper. In this work, we further study the problem of designing deep architectures for GCNs. Firstly, we introduce the Higher Order Graph Recurrent Networks (HOGRNs), which can unify most existing architectures of GCNs. Then we show that ResGCN and DenseGCN are special cases of HOGRNs. To enjoy the benefits from both residual connections and dense connections and compensate for the drawbacks from each other, we propose Dual Path Graph Convolutional Networks (DPGCNs), which exploit a new topology of connection paths internally. In DPGCNs, we maintain both a residual path and a densely connected path while learning the graph representations. Extensive experiments on OGB datasets demonstrate superior performances of the proposed DPGCNs over competitive baseline methods on the large-scale graph learning tasks of node property prediction and graph property prediction.
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 | 0.000 | 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 | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 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".