Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
156 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Causal Graph ODE: Continuous Treatment Effect Modeling in Multi-agent Dynamical Systems (2403.00178v1)

Published 29 Feb 2024 in cs.LG and cs.AI

Abstract: Real-world multi-agent systems are often dynamic and continuous, where the agents co-evolve and undergo changes in their trajectories and interactions over time. For example, the COVID-19 transmission in the U.S. can be viewed as a multi-agent system, where states act as agents and daily population movements between them are interactions. Estimating the counterfactual outcomes in such systems enables accurate future predictions and effective decision-making, such as formulating COVID-19 policies. However, existing methods fail to model the continuous dynamic effects of treatments on the outcome, especially when multiple treatments (e.g., "stay-at-home" and "get-vaccine" policies) are applied simultaneously. To tackle this challenge, we propose Causal Graph Ordinary Differential Equations (CAG-ODE), a novel model that captures the continuous interaction among agents using a Graph Neural Network (GNN) as the ODE function. The key innovation of our model is to learn time-dependent representations of treatments and incorporate them into the ODE function, enabling precise predictions of potential outcomes. To mitigate confounding bias, we further propose two domain adversarial learning-based objectives, which enable our model to learn balanced continuous representations that are not affected by treatments or interference. Experiments on two datasets (i.e., COVID-19 and tumor growth) demonstrate the superior performance of our proposed model.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (44)
  1. Temporal Domain Generalization with Drift-Aware Dynamic Neural Networks. arXiv preprint arXiv:2205.10664 (2022).
  2. Alexis Bellot and Mihaela Van Der Schaar. 2021. Policy analysis using synthetic controls in continuous-time. In International Conference on Machine Learning. PMLR, 759–768.
  3. Estimating counterfactual treatment outcomes over time through adversarially balanced representations. International Conference on Learning Representations (2020).
  4. Estimating counterfactual treatment outcomes over time through adversarially balanced representations. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020.
  5. A method for assessing the quality of a randomized control trial. Controlled clinical trials 2, 1 (1981), 31–49.
  6. Neural Ordinary Differential Equations. In Advances in Neural Information Processing Systems 31. 6571–6583.
  7. Predicting the impact of treatments over time with uncertainty aware neural differential equations.. In International Conference on Artificial Intelligence and Statistics. PMLR, 4705–4722.
  8. Prediction of treatment response for combined chemo-and radiation therapy for non-small cell lung cancer patients using a bio-mathematical model. Scientific reports 7, 1 (2017), 13542.
  9. Neural ordinary differential equations for intervention modeling. arXiv preprint arXiv:2010.08304 (2020).
  10. Variational Graph Recurrent Neural Networks. In Advances in Neural Information Processing Systems 32. 10701–10711.
  11. Heterogeneous Graph Transformer. In Proceedings of the 2020 World Wide Web Conference.
  12. Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment. In Annual Meeting of the Association for Computational Linguistics (ACL).
  13. Learning Continuous System Dynamics from Irregularly-Sampled Partial Observations. In Advances in Neural Information Processing Systems.
  14. Coupled graph ode for learning interacting system dynamics. In The 27th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (SIGKDD).
  15. Generalizing graph ode for learning complex system dynamics across environments. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 798–809.
  16. Concept2Box: Joint Geometric Embeddings for Learning Two-View Knowledge Graphs. In Findings of the Association for Computational Linguistics: ACL 2023. Association for Computational Linguistics, 10105–10118.
  17. TANGO: Time-Reversal Latent GraphODE for Multi-Agent Dynamical Systems. https://openreview.net/forum?id=H7R0z6V9fR
  18. CF-GODE: Continuous-Time Causal Inference for Multi-Agent Dynamical Systems. In 29th SIGKDD Conference on Knowledge Discovery and Data Mining.
  19. Song Jiang and Yizhou Sun. 2022. Estimating Causal Effects on Networked Observational Data via Representation Learning. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management. 852–861.
  20. Multi-scale Dynamic Human Mobility Flow Dataset in the U.S. during the COVID-19 Epidemic. Scientific Data 1-13 (2020). Issue 390.
  21. Diederik P. Kingma and Max Welling. 2014. Auto-Encoding Variational Bayes.. In ICLR.
  22. Neural Relational Inference for Interacting Systems. arXiv preprint arXiv:1802.04687 (2018).
  23. Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In ICLR’17.
  24. Bryan Lim. 2018. Forecasting treatment responses over time using recurrent marginal structural networks. advances in neural information processing systems 31 (2018).
  25. Ilya Loshchilov and Frank Hutter. [n. d.]. Decoupled Weight Decay Regularization. In International Conference on Learning Representations.
  26. CARE: Modeling Interacting Dynamics Under Temporal Environmental Variation. In Thirty-seventh Conference on Neural Information Processing Systems.
  27. HOPE: high-order graph ODE for modeling interacting dynamics. In Proceedings of the 40th International Conference on Machine Learning (ICML’23). 16 pages.
  28. Assessing the Causal Impact of COVID-19 Related Policies on Outbreak Dynamics: A Case Study in the US. In Proceedings of the ACM Web Conference 2022 (WWW ’22). 2678–2686.
  29. Learning causal effects on hypergraphs. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 1202–1212.
  30. Causal Transformer for Estimating Counterfactual Outcomes. In International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA (Proceedings of Machine Learning Research, Vol. 162). PMLR, 15293–15329.
  31. A probabilistic model for the numerical solution of initial value problems. In Statistics and Computing. 99–122.
  32. Judea Pearl. 2009. Causality. Cambridge university press.
  33. Graph neural ordinary differential equations. arXiv preprint arXiv:1911.07532 (2019).
  34. Marginal structural models and causal inference in epidemiology. , 550–560 pages.
  35. Latent Ordinary Differential Equations for Irregularly-Sampled Time Series. In Advances in Neural Information Processing Systems 32. 5320–5330.
  36. Donald B Rubin. 1978. Bayesian inference for causal effects: The role of randomization. The Annals of statistics (1978), 34–58.
  37. Learning to Simulate Complex Physics with Graph Networks. In Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13-18 July 2020, Virtual Event. 8459–8468.
  38. DySAT: Deep Neural Representation Learning on Dynamic Graphs via Self-Attention Networks. In WSDM’20.
  39. Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equations. In International Conference on Machine Learning. PMLR, 19497–19521.
  40. Attention is All you Need. In Advances in Neural Information Processing Systems 30. 5998–6008.
  41. Graph Attention Networks. ICLR’18 (2018).
  42. How Powerful are Graph Neural Networks?. In ICLR’19.
  43. Chengxi Zang and Fei Wang. 2020. Neural dynamics on complex networks. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 892–902.
  44. Yunhao Zhang and Junchi Yan. 2023. Crossformer: Transformer Utilizing Cross-Dimension Dependency for Multivariate Time Series Forecasting. In International Conference on Learning Representations.
Citations (3)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now