Charles Assaad

Junior professor chair @Inserm @Sorbonne_Univ_ | Head of the CIPHOD team

[Charles Assaad @ckassaad]

📄 Read the full paper: https://t.co/QkKokjoWwE

🎥 Watch Simon's 10-min summary: https://t.co/EmFOHSWvYB

📚 More of our team's work: https://t.co/TXL1mcVz68

#CausalInference #DoCalculus #AI #Causality #TMLR

(5/5)

[Charles Assaad @ckassaad]

🚨 New paper with @SimonMFerreira just published in @TmlrOrg !
We show that do-calculus applies cluster graphs even in the presence of cycles.
A big step forward for causal inference when a full DAG isn't available.
More details👇 (1/5)

[Charles Assaad @ckassaad]

The classical hedge structure (used to characterize non-identifiability in DAGs) fails in this setting.
So we introduce:
✅ the SC-hedge, a new structure that flags non-identifiability in cluster graphs.
(4/5)

[Charles Assaad @ckassaad]

🚨 New paper @TmlrOrg !
This paper introduces the SCG-front-door criterion to identify micro total effects from Summary Causal Graphs even in the presence of:
✅Latent confounding,
✅Instantaneous effects
✅Cycles

📄 read more: https://t.co/z7ip0Jni1M

#CausalInference

[Charles Assaad @ckassaad]

In the second paper, we show how to identify total or direct effects using difference graphs. I’ll be presenting this work at @Conf_CLeaR

For more details about the first paper👉🏻 https://t.co/K6DeIxlkjZ
For more details about the second paper👉🏻 https://t.co/DlvRAHbPfX

(2/2)

[Charles Assaad @ckassaad]

I’m thrilled to share that we’ve already had two papers accepted in 2025!

In our first paper, we demonstrated that do-calculus is applicable to Summary Causal Graphs (SCGs) when analyzing macro causal effects.
This work will be presented by @SimonMFerreira at @RealAAAI.

(1/2)

[Charles Assaad @ckassaad]

Congratulations to @LeiZAN12 for successfully defending his PhD! 🎉
Lei was the first PhD I co-supervised (with Eric Gaussier and Emilie Devijver), and I couldn’t be prouder of his achievement. Lei had many contributions that made causal discovery applicable in IT monitoring!

[Daria Bystrova @dabystrova]

Great talks and discussions! Huge thanks to the organizers for hosting such a wonderful event and making it accessible via live streaming. 👏👏

[Accepted papers at TMLR @TmlrPub]

Causal Discovery from Time Series with Hybrids of Constraint-Based and Noise-Based Algorithms

Daria Bystrova, Charles K. Assaad, Julyan Arbel, Emilie Devijver, Eric Gaussier, Wilfried Thuiller.

Action editor: Mingming Gong.

https://t.co/xK632bUREt

#graphs #

[Charles Assaad @ckassaad]

Andreas Gerhardus, @JonasChoice, and @oanaucs opening the second edition of the causal inference for time series workshop @UncertaintyInAI in Barcelona 🇪🇸

For more details about the workshop 👉🏻 https://t.co/xsYR9AWYuq

[Charles Assaad @ckassaad]

Honored to be selected for the second year in a row as one of the Top Reviewers @UncertaintyInAI ! This year, 50 top reviewers were chosen out of ~750 as reviewers. Congratulations to all who made the list! For the full list, check the following link: https://t.co/MEUskvIeP9

[Charles Assaad @ckassaad]

Excited to share that our paper, "Identifiability of Total Effects from Abstractions of Time Series Causal Graphs," has been accepted to @UncertaintyInAI! 🎉 If you're attending #UAI2024, stop by my poster tomorrow. Can't make it? Check it out online: https://t.co/UydHi8rPQx

[Charles Assaad @ckassaad]

@osmanmian The topic was highly inspired from your AISTATS 2023 paper 😎

[Charles Assaad @ckassaad]

🚨 Job alert - PhD in Federated causal discovery and causal representation in a high dimensional setting with applications to epidemiology 🚨

👉 Description: https://t.co/JzQ5fByzxb
👉 Deadline: June 13th

#causality #AI #epidemiology #health #phd @Inserm @Sorbonne_Univ_

[Charles Assaad @ckassaad]

We presented hybrid methods that combine principles from both constraint-based and noise-based methods, offering greater robustness to assumption violations. Our experimental results highlight the effectiveness of these hybrid methods across a diverse range of datasets.

2/2

[Charles Assaad @ckassaad]

Thrilled to share that our paper on hybrid causal discovery in time series, co-authored with @dabystrova , @JulyanArbel, @e_devijver, Eric Gaussier and @Wil_Thuiller, has been accepted to @TmlrPub ! 🎉 #CausalInference #TimeSeries #AI

The paper 👉🏻
https://t.co/P7OsfKmlah
1/2

[Jakob Runge @runge_jakob]

Contribute to the 2nd workshop on causal inference for time series at UAI, this year on July 19 in Barcelona! Deadline for submissions is May 19, less than 10 days to go! Looking forward to another successful event! Details: https://t.co/Qy9S0phhZs #CI4TS #UAI2024

[Charles Assaad @ckassaad]

Exciting news!! The list of confirmed speakers for the upcoming second edition of the workshop on causal inference for time series data @UncertaintyInAI includes Gustau Camps-Valls, @_MiguelHernan, @saramagliacane, Christian Reimers, @JurajBodik, and Christine Winther Bang.

[Charles Assaad @ckassaad]

Happy to announce the 2nd edition of the workshop on causal inference for time series data @UncertaintyInAI in June this year, co-organized by @oanaucs, @JonasChoice @runge_jakob, @huang_biwei, myself and others! The workshop includes a call for papers 👉🏻 https://t.co/ZqFBU8cqkW

[Charles Assaad @ckassaad]

🚨
Please note that the workshop will be held on July, not June.
🚨
My apologies for the error.