Next Up on 07.December '22: Luigi Gresele, Ph.D. Candidate @ MPI:IS with Causal Inference Through the Structural Causal Marginal Problem @ ICML 2022
Logo of Causality Discussion Group

Join the Discussion!

We get together with the authors of papers in Causality x AI/ML to discuss their papers in a lively group discussion. We meet weekly on Wednesday at 15:30 UTC / 16:30 CEST/CET in summer/winter / 10:30 EST / 23:30 JST.

Join the Session (Zoom)
Join the Community (Slack)
Join the Mailing List (G-Groups)
⬇️ Scroll Down for More ⬇️

"If the discussions become too causal, then we might as well make it more casual." (warning: a joke that requires looking closely)

🌐 Everything to be found in our Slack Community:
We keep a long list of interesting papers (see list in
channel at “List of Potential Next Paper Discussions”), from which we vote for our session papers (vote at
channel), and also recordings from our past sessions all self-enclosed in the Slack community (find in

Past Sessions (see #recordings):

  • Session 30.11.2022 | Selecting Data Augmentation for Simulating Interventions | Discussant: Maximilian Ilse
  • Session 23.11.2022 | On Disentangled Representations Learned from Correlated Data | Discussant: Frederik Träuble
  • Session 16.11.2022 | Causal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Repr. Learning | Discussant: Sumedh Sontakke
  • Session 09.11.2022 | Causal Machine Learning: A Survey and Open Problems | Discussants: Jean Kaddour, Aengus Lynch
  • Session 02.11.2022 | A Critical Look at the Consistency of Causal Estimation with Deep Latent Variable Models | Discussant: Severi Rissanen
  • Session 26.10.2022 | Nonlinear Invariant Risk Minimization: A Causal Approach | Discussant: Chaochao Lu
  • Session 19.10.2022 | CausalVAE: Disentangled Representation Learning via Neural Structural Causal Models | Discussant: Mengyue Yang
  • Session 12.10.2022 | Weakly Supervised Causal Representation Learning | Discussant: Johann Brehmer
  • Session 05.10.2022 | Towards Causal Representation Learning | Discussant: Anirudh Goyal
  • Session 21.09.2022 | Selection Collider Bias in Large Language Models | Discussant: Emily McMilin
  • Session 14.09.2022 | The Causal-Neural Connection: Expressiveness, Learnability, and Inference | Discussants: Kai-Zhan Lee, Kevin Xia
  • Session 07.09.2022 | Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style | Discussant: Julius von Kügelgen
  • Session 31.08.2022 | Interventions, Where and How? Experimental Design for Causal Models at Scale | Discussants: Panagiotis Tigas and Yashas Annadani
  • Session 24.08.2022 | Beware of the Simulated DAG! Causal Discovery Benchmarks May Be Easy To Game | Discussant: Alexander Reisach
  • Session 17.08.2022 | Effect Identification in Cluster Causal Diagrams | Discussants: Tara Anand and Adèle Ribeiro
  • Session 10.08.2022 | Can Foundation Models Talk Causality? | Discussant: Moritz Willig
  • Session 03.08.2022 | Causal Conceptions of Fairness and their Consequences | Discussants: Hamed Nilforoshan and Johann Gaebler
  • Session 28.07.2022 | Bayesian Causal Discovery under Unknown Interventions | Discussant: Alexander Hägele
  • Session 20.07.2022 | Counterfactual Fairness | Discussant: Toon Vanderschueren

Useful Resources:

Are you interested in Graphs and Geometry for Machine Learning?

If so, then consider joining the Learning on Graphs and Geometry Reading Group.