F-FOMAML: GNN-Enhanced Meta-Learning for Peak Period Demand Forecasting with Proxy Data
Not on the map. Why?
Abstract (arXiv)
Demand prediction is a crucial task for e-commerce and physical retail businesses, especially during high-stake sales events. However, the limited availability of historical data from these peak periods poses a significant challenge for traditional forecasting methods. In this paper, we propose a novel approach that leverages strategically chosen proxy data reflective of potential sales patterns from similar entities during non-peak periods, enriched by features learned from a graph neural networks (GNNs)-based forecasting model, to predict demand during peak events. We formulate the demand prediction as a meta-learning problem and develop the Feature-based First-Order Model-Agnostic Meta-Learning (F-FOMAML) algorithm that leverages proxy data from non-peak periods and GNN-generated relational metadata to learn feature-specific layer parameters, thereby adapting to demand forecasts for peak events. Theoretically, we show that by considering domain similarities through task-specific metadata, our model achieves improved generalization, where the excess risk decreases as the number of training tasks increases. Empirical evaluations on large-scale industrial datasets demonstrate the superiority of our approach. Compared to existing state-of-the-art models, our method demonstrates a notable improvement in demand prediction accuracy, reducing the Mean Absolute Error by 26.24% on an internal vending machine dataset and by 1.04% on the publicly accessible JD.com dataset.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 29 of its 51 references that are in the map. First posted on arXiv 23 Jun 2024.
Builds on
29 of 51 references.
References · 29
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
- 2017Prototypical Networks for Few-shot Learningcited by 3,015
- 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
- 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,367
- 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
- 2016Matching Networks for One Shot Learningcited by 2,255
- 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,329
- 2017Adversarial Discriminative Domain Adaptationcited by 1,311
- 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
- 2018On First-Order Meta-Learning Algorithmscited by 1,018
17 more
- 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,013
- 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 879
- 2019Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecastingcited by 761
- 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 753
- 2017Meta-SGD: Learning to Learn Quickly for Few-Shot Learningcited by 379
- 2017A Multi-Horizon Quantile Recurrent Forecastercited by 211
- 2021Discrete Graph Structure Learning for Forecasting Multiple Time Seriescited by 171
- 2020Deep Transformer Models for Time Series Forecasting: The Influenza Prevalence Casecited by 129
- 2017Dipole: Diagnosis Prediction in Healthcare via Attention-based Bidirectional Recurrent Neural Networkscited by 116
- 2019Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulationcited by 103
- 2020Transfer Learning of Graph Neural Networks with Ego-graph Information Maximizationcited by 93
- 2020Meta-learning for mixed linear regressioncited by 44
- 2020Robust Meta-learning for Mixed Linear Regression with Small Batchescited by 41
- 2020MQTransformer: Multi-Horizon Forecasts with Context Dependent and Feedback-Aware Attentioncited by 29
- 2021Conditional Neural Relational Inference for Interacting Systemscited by 28
- 2020Probabilistic Time Series Forecasting with Structured Shape and Temporal Diversitycited by 9
- 2015Electricity Demand Forecasting by Multi-Task Learningcited by 5
Built on by
Citing papers per year: 2024: 1.
1 paper.