New research explores causal inference and data synthesis for complex data types · 8 sources tracked
ByPulseAugur Editorial·[11 sources]·
Several new research papers explore advancements in causal inference and data synthesis, particularly for tabular and temporal data. One paper introduces a benchmark framework to evaluate tabular synthesis models based on high-order structural causal information, highlighting gaps in current state-of-the-art models. Another work proposes "Lifted Causal Inference" to efficiently compute causal effects in relational domains using parametric causal factor graphs. Additionally, research investigates the estimation-prediction tradeoff in causal probabilistic temporal graphs, suggesting that predictive accuracy alone may not fully reflect a model's understanding of causal mechanisms. Further work introduces "Causal Foundation Models" that can incorporate domain knowledge, and a method for doubly robust adaptive conformal inference for causal effects under temporal dependence.
AI
IMPACT
These papers advance methods for understanding and generating complex data, potentially improving AI model reliability and interpretability.
RANK_REASON
Cluster consists of multiple arXiv pre-print papers on causal inference and data synthesis.
arXiv:2602.22083v2 Announce Type: replace-cross Abstract: Causal identification functionals often require integration over conditional densities of continuous variables, such as those arising in nonparametric identification theory of total and mediated causal effects in DAGs with…
arXiv cs.LG
TIER_1English(EN)·Yufei Wu, Zhiying Gu, Alex Deng, Jacob Zhu, Linsha Chen·
arXiv:2606.30992v1 Announce Type: cross Abstract: Multicollinearity is a long lasting challenge in observational causal inference, especially in regressions -- highly correlated independent variables make it hard to isolate their individual impacts on outcomes of interest. While …
arXiv:2606.28225v1 Announce Type: new Abstract: Temporal link prediction is usually evaluated by predictive performance on unseen edges, but in probabilistic temporal graphs this criterion can conflate model error with irreducible uncertainty. We study this issue by characterisin…
arXiv:2606.28024v1 Announce Type: new Abstract: Lifted inference exploits indistinguishabilities in probabilistic graphical models by using a representative for indistinguishable objects, thereby speeding up query answering while maintaining exact answers. In this article, we sho…
arXiv cs.MA (Multiagent)
TIER_1English(EN)·Aniq Ur Rahman·
Temporal link prediction is usually evaluated by predictive performance on unseen edges, but in probabilistic temporal graphs this criterion can conflate model error with irreducible uncertainty. We study this issue by characterising an inherent estimation--prediction tradeoff in…
Lifted inference exploits indistinguishabilities in probabilistic graphical models by using a representative for indistinguishable objects, thereby speeding up query answering while maintaining exact answers. In this article, we show how lifting can be applied to efficiently comp…
arXiv cs.LG
TIER_1English(EN)·Arik Reuter, Anish Dhir, Cristiana Diaconu, Jake Robertson, Ole Ossen, Frank Hutter, Adrian Weller, Mark van der Wilk, Bernhard Sch\"olkopf·
arXiv:2602.14972v2 Announce Type: replace Abstract: Estimating causal quantities traditionally relies on bespoke estimators tailored to specific assumptions. Recently proposed Causal Foundation Models (CFMs) promise a more unified approach by amortising causal discovery and infer…
arXiv:2606.30500v1 Announce Type: new Abstract: We propose doubly robust adaptive conformal inference (DR-ACI), which constructs prediction intervals for doubly robust pseudo-outcomes under temporal dependence.
We propose doubly robust adaptive conformal inference (DR-ACI), which constructs prediction intervals for doubly robust pseudo-outcomes under temporal dependence.
arXiv stat.ML
TIER_1English(EN)·Anna Guo, Lin Liu, David Benkeser, Razieh Nabi·
arXiv:2512.19861v2 Announce Type: replace-cross Abstract: Unmeasured confounding can render identification strategies based on adjustment functionals invalid. We study the "Napkin" graph, a causal structure that encapsulates features of M-bias, instrumental variables, and classic…
