Toward Scalable and High-Performance GNN-Based Traffic Engineering with Free Path Selection
Bibliographic record
Abstract
Traffic engineering (TE) is widely used to optimize network performance in modern networks. Typically, TE is formulated as a multiple-commodity flow (MCF) optimization problem and solved using mathematical solvers or machine learning approaches, but it becomes unscalable as the network size grows. Existing methods often limit available paths for flow allocation to speed up problem-solving, but this compromises TE performance. Achieving both high performance and fast decisionmaking with free path selection remains a significant challenge. This paper proposes TELD, a scalable and high-performance TE framework with free path selection. TELD leverages Graph Neural Networks (GNNs) that are widely proven with high efficiency in capturing network-specific characteristics and enabling faster decision-making than mathematical solvers. Our key idea is to reformulate the MCF problem into a learningfriendly representation and integrate TE constraints directly into GNN training and inference. The key challenge here is how to efficiently combine the problem reformulation with GNN. TELD tackles this with two critical designs. First, observing that GNNs work better with continuous features, TELD relaxes the freepath MCF formulation by treating flow allocation variables as continuous rather than discrete. Second, TELD introduces a multi-constraint hybrid GNN and a result fine-tuning mechanism to further improve GNN efficiency in TE. Extensive experiments show that TELD outperforms the state-of-the-art GNN-based TE framework by$\sim 55\%$and reduces decision latency by three orders of magnitude compared to mathematical solvers.
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 | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.003 | 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".