# Structured Learning of Compositional Sequential Interventions

arXiv: https://arxiv.org/abs/2406.05745 · HTML: https://mlsanity.com/paper/2406.05745/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 51 references that are in the map.
- First posted on arXiv 9 Jun 2024.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Conformal Prediction Under Covariate Shift](https://mlsanity.com/paper/1904.06019/) (2019)
- [Adaptive Conformal Inference Under Distribution Shift](https://mlsanity.com/paper/2106.00170/) (2021)
- [Conformal Inference of Counterfactuals and Individual Treatment Effects](https://mlsanity.com/paper/2006.06138/) (2020)
- [Conformal Prediction: a Unified Review of Theory and New Challenges](https://mlsanity.com/paper/2005.07972/) (2020)
- [Neural Variational Inference and Learning in Belief Networks](https://mlsanity.com/paper/1402.0030/) (2014)
- [Conformal PID Control for Time Series Prediction](https://mlsanity.com/paper/2307.16895/) (2023)
- [Identifiability Guarantees for Causal Disentanglement from Soft Interventions](https://mlsanity.com/paper/2307.06250/) (2023)
- [Causal Matrix Completion](https://mlsanity.com/paper/2109.15154/) (2021)
- [Causal Bayesian Optimization](https://mlsanity.com/paper/2005.11741/) (2020)
- [Causal Effect Inference for Structured Treatments](https://mlsanity.com/paper/2106.01939/) (2021)
- [An Exact and Robust Conformal Inference Method for Counterfactual and Synthetic Controls](https://mlsanity.com/paper/1712.09089/) (2017)
- [Off-Policy Evaluation for Large Action Spaces via Conjunct Effect Modeling](https://mlsanity.com/paper/2305.08062/) (2023)
- [Synthetic Interventions](https://mlsanity.com/paper/2006.07691/) (2020)
- [Identifying Representations for Intervention Extrapolation](https://mlsanity.com/paper/2310.04295/) (2023)
- [The Music Streaming Sessions Dataset](https://mlsanity.com/paper/1901.09851/) (2018)
- [Causal Imputation via Synthetic Interventions](https://mlsanity.com/paper/2011.03127/) (2020)
- [Conformalized matrix completion](https://mlsanity.com/paper/2305.10637/) (2023)
- [POTEC: Off-Policy Learning for Large Action Spaces via Two-Stage Policy Decomposition](https://mlsanity.com/paper/2402.06151/) (2024)
- [Synthetic Combinations: A Causal Inference Framework for Combinatorial Interventions](https://mlsanity.com/paper/2303.14226/) (2023)
- [Parameterizing and Simulating from Causal Models](https://mlsanity.com/paper/2109.03694/) (2021)
- [Intervention Generalization: A View from Factor Graph Models](https://mlsanity.com/paper/2306.04027/) (2023)
- [Semiparametric Causal Sufficient Dimension Reduction Of Multidimensional Treatments](https://mlsanity.com/paper/1710.06727/) (2017)
- [Causal Inference with High-dimensional Discrete Covariates](https://mlsanity.com/paper/2405.00118/) (2024)

## Built on by (most cited first, 2 of 2)

- [Causal Discovery from Time-Series Data with Short-Term Invariance-Based Convolutional Neural Networks](https://mlsanity.com/paper/2408.08023/) (2024)
- [Causal Fine-Tuning under Latent Confounded Shift](https://mlsanity.com/paper/2410.14375/) (2024)

## Abstract (arXiv)

We consider sequential treatment regimes where each unit is exposed to combinations of interventions over time. When interventions are described by qualitative labels, such as "close schools for a month due to a pandemic" or "promote this podcast to this user during this week", it is unclear which appropriate structural assumptions allow us to generalize behavioral predictions to previously unseen combinations of interventions. Standard black-box approaches mapping sequences of categorical variables to outputs are applicable, but they rely on poorly understood assumptions on how reliable generalization can be obtained, and may underperform under sparse sequences, temporal variability, and large action spaces. To approach that, we pose an explicit model for composition, that is, how the effect of sequential interventions can be isolated into modules, clarifying which data conditions allow for the identification of their combined effect at different units and time steps. We show the identification properties of our compositional model, inspired by advances in causal matrix factorization methods. Our focus is on predictive models for novel compositions of interventions instead of matrix completion tasks and causal effect estimation. We compare our approach to flexible but generic black-box models to illustrate how structure aids prediction in sparse data conditions.