UME: A Unified Meta-Generalization Framework for Cross-Domain ETA

arXiv:2606.00979 · cs.LG · Submitted 2026-05-31 · Read on arXiv

cs.LG

Submitted: 2026-05-31

Updated: 2026-05-31

Journal ref: KDD '26: Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Vol. 2 (2026), 8112-8123

DOI: 10.1145/3770855.3818500

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Generalization — 71× in this paper · explained in 13 episodes
• Domain Generalization — 24× in this paper
• Distillation — 21× in this paper · explained in 2 episodes
• Meta-learning — 14× in this paper · explained in 2 episodes
• Hypernetwork — 11× in this paper · explained in 2 episodes
• Ablation — 10× in this paper · explained in 1 episode
• Adaptation — 9× in this paper · explained in 1 episode
• Calibration — 9× in this paper · explained in 7 episodes
• Ablation Studies — 7× in this paper · explained in 1 episode
• Accuracy — 6× in this paper · explained in 1 episode
• Knowledge Distillation — 6× in this paper · explained in 11 episodes
• Multi-Domain Learning — 6× in this paper
• Domain Adaptation — 5× in this paper · explained in 5 episodes
• Embeddings — 5× in this paper · explained in 2 episodes
• Hong Kong — 4× in this paper
• Unified Dual-Branch Network — 4× in this paper
• Domain Shift — 3× in this paper · explained in 4 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Transfer Learning — 3× in this paper · explained in 10 episodes
• Unified Framework — 3× in this paper · explained in 5 episodes
• Accurate Estimated Time of Arrival — 2× in this paper
• Aggregation — 2× in this paper · explained in 1 episode
• Distribution Shift — 2× in this paper · explained in 5 episodes
• International Conference on Data Engineering — 2× in this paper
• Loss Function — 2× in this paper · explained in 2 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Abstraction — 1× in this paper · explained in 1 episode
• Actual Time of Arrival — 1× in this paper
• Adam — 1× in this paper · explained in 2 episodes
• Aleatoric Uncertainty — 1× in this paper · explained in 4 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Bad Case Rate — 1× in this paper
• Composite Loss Function — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Feature Extraction — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Gradient Flow — 1× in this paper · explained in 2 episodes
• Heteroscedasticity — 1× in this paper · explained in 2 episodes
• Mixture of Experts — 1× in this paper · explained in 2 episodes
• Negative Log-Likelihood — 1× in this paper
• Probability Integral Transform — 1× in this paper
• Sparsity — 1× in this paper · explained in 4 episodes
• United Arab Emirates — 1× in this paper
• Zero-Shot Generalization — 1× in this paper · explained in 5 episodes

Sources

• Invariant Risk Minimization
• HMOE: Hypernetwork-based Mixture of Experts for Domain Generalization
• Cross-City Transfer Learning for Deep Spatio-Temporal Prediction
• A Unified Perspective on Multi-Domain and Multi-Task Learning

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks