Highlights
News
-
Collaboration with Honda Research Institute
The paper Towards Probabilistic Clearance, Explanation and Optimization by Simon Kohaut, Benedict Flade, Devendra Singh Dhami, Julian Eggert and Kristian Kersting in collaboration with the Honda Research Institute has been accepted at the International Conference on Unmanned Aircraft Systems (ICUAS)
-
Multiple articles accepted at machine learning journals
Enhancing performance of vision transformers on small datasets through local inductive bias incorporation by Ibrahim Batuhan Akkaya, Senthilkumar S. Kathiresan, Elahe Arani, and Bahram Zonooz has been published at the Pattern Recognition Journal IMEX-Reg: Implicit-Explicit Regularization in the Function Space for Continual Learning by Prashant Bhat, Bharath Renjith, Elahe Arani, and Bahram Zonooz has been published at Transactions on Machine Learning ResearchAMLB: an AutoML Benchmark by Pieter Gijsbers, Marcos L. P. Bueno, Stefan Coors, Erin LeDell, Sébastien Poirier, Janek Thomas, Bernd Bischl, and Joaquin Vanschoren has been published at Journal of Machine Learning ResearchMachine Learning meets Kepler: Inverting Kepler’s Equation for All vs All Conjunction Analysis by Kevin Otto, Simon Burgis, Kristian Kersting, Reinhold Bertrand, and Devendra Singh Dhami has been published in Machine Learning: Science and Technology (MLST)Neuro-Symbolic Predicate Invention: Learning Relational Concepts from Visual Scenes by Jingyuan Sha, Hikaru Shindo, Kristian Kersting, and Devendra Singh Dhami has been published in Neurosymbolic Artificial Intelligence
-
Multiple papers have been accepted at CoLLAs 2024
The following papers will be presented at the Third Conference on Lifelong Learning Agents:Beyond Unimodal Learning: The Importance of Integrating Multiple Modalities for Lifelong Learning by Fahad Sarfraz, Bahram Zonooz, Elahe AraniMitigating Interference in the Knowledge Continuum through Attention-Guided Incremental Learning by Prashant Bhat, Bharath Renjith, Elahe Arani, Bahram ZonoozLearning to learn without forgetting using attention by Anna Vettoruzzo, Joaquin Vanschoren, Mohamed-Rafik Bouguelia, and Thorsteinn S. Rögnvaldsson
External
-
Multiple papers accepted at ICML 2024
Our cluster will be greatly represented at ICML! The following papers will be presented in Vienna: Provably Efficient Exploration in Constrained Reinforcement Learning: Posterior Sampling Is All You Need by Danil Provodin, Maurits Kaptein and Mykola Pechenizkiy.MALIBO: Meta-learning for Likelihood-free Bayesian Optimization by Jiarong Pan, Stefan Falkner, Felix Berkenkamp, and Joaquin VanschorenTrustLLM: Trustworthiness in Large Language Models by Lichao Sun et al. including Joaquin VanschorenScalable Safe Policy Improvement for Factored Multi-Agent MDPs by Federico Bianchi, Edoardo Zorzi, Alberto Castellini, Thiago D. Simão, Matthijs T. J. Spaan, and Alessandro FarinelliGradual Divergence for Seamless Adaptation: A Novel Domain Incremental Learning Method by Kishaan Jeeveswaran, Elahe Arani, and Bahram ZonoozCongratulations to all of our amazing researchers who have submitted their work to this top-tier conference!
External
-
Two works to be presented at ICDE'24 and MulTiSA'24 (co-located with ICDE)
Join us at ICDE to hear a lightning talk titled "Multivariate similarity search - a call for a new breed of similarity search algorithms" and a workshop talk at MulTiSA'24 titled "Beyond the Dimensions: A Structured Evaluation of Multivariate Time Series Distance Measures" by our Database group colleagues, Odysseas Papapetrou and Jens d'Hondt.
External
-
A workshop at ICDE'24
Our member, Odysseas Papapetrou, is organizing the first Multivariate Time Series Analytics workshop (MulTiSA'24), at ICDE'24. It is not too late to register and join us, to hear about the state of the art on multivariate time series.
External
-
PhD position with the Database group on data streams
The Database group has a 5-years PhD vacancy on synopses for data stream processing. Have a look here for more details and for instructions to apply: https://jobs.tue.nl/en/vacancy/phd-on-streaming-data-management-1078132.htmlWe will be at ICDE'24 in Utrecht. If you are there and want to have an informal chat about this position, send us an email at o.papapetrou@tue.nl
External
-
ICML 2024 GRaM workshop (July)
Our member Jakub Tomczak is co-organizing the first edition of GRaM: Geometry-grounded Representation Learning and Generative Modeling Workshop at ICML 2024 in Vienna, Austria.
For more info, see the link.
External
-
Two papers accepted at UAI 2024
In the paper "Pix2Code: Learning to Compose Neural Visual Concepts as Programs", Antonia Wüst, Wolfgang Stammer, Quentin Delfosse, Devendra Singh Dhami, and Kristian Kersting propose Pix2Code, a framework that extends program synthesis to visual relational reasoning by utilizing the abilities of explicit, compositional symbolic and implicit neural representations.In the paper chiSPN: Characteristic Interventional Sum-Product Networks for Causal Inference in Hybrid Domains, Harsh Poonia, Moritz Willig, Zhongjie Yu, Matej Zečević, Kristian Kersting, and Devendra Singh Dhami extend sum-product networks for causal inference to hybrid domain i.e. domain with heterogeneous data. chiSPN provides a unified view for discrete and continuous random variables through the Fourier–Stieltjes transform of the probability measures thereby making it possible to do causal inference from both types of data at once.
External
-
Workshop on Explainable AI (23/05)
The ELA AI Triangle (EAISI, Leuven.AI, and RWTH AI Center) Workshop series on Explainable AI will kick off on May 23rd at TU Eindhoven.
The first workshop in the series will focus on theories, methods,
and applications of (neuro-) symbolic AI that enable and/or leverage
explainability.
However, all researchers interested in this and other XAI
subareas are welcome to attend and contribute. Registration is free! See link for more info.
External
-
Mini-symposium "Is knowledge useful?" (19/04)
On April 19th we will hold a mini-symposium titled "Is knowledge useful?". We will discuss how to represent knowledge, and when and how to use it for different applications. See link for details of the event!
External
-
Colloquium on uncertainties in AI (Feb 5th)
On Feb 5 the UAI group is organizing a colloquium on uncertainties in AI, together with partners at TU/e, RWTH Aachen Uni & KU Leuven. The event is held at MetaForum 4.208, 15:45-17:15, and open to everyone! See link for more info
External
-
Two papers accepted at AISTATS 2024
In the paper "Probabilistic Integral Circuits", Gennaro Gala, Cassio de Campos, Robert Peharz, Antonio Vergari, and Erik Quaeghebeur show how to represent and perform inference on continuous latent variable models in the language of circuits.In the paper "Attention-based Multi-instance Mixed Models", Jan P. Engelmann, Alessandro Palma, Jakub M. Tomczak, Fabian J Theis, and Francesco Paolo Casale present GMIL, a framework integrating Generalized Linear Mixed Models (GLMM) and Multiple Instance Learning (MIL), that upholds the advantages of linear models while modeling data heterogeneity uisng pre-defined embeddings.
External
-
Four papers accepted at ICLR 2024
In the paper "Learning Large DAGs is Harder than you Think: Many Losses are Minimal for the Wrong DAG", Jonas Seng, Matej Zečević, Devendra Singh Dhami, and Kristian Kersting consider the structure learning problem, which is hard for even simple DAG’s. They formally proved that measurement scale can decide which DAGs will minimize the MMSE or log-likelihood based losses such as ELBO and BIC and thus should be treated with care.
In the paper "Conserve-Update-Revise to Cure Generalization and Robustness Trade-off in Adversarial Training", Shruthi Gowda, Bahram Zonooz, and Elahe Arani propose a selective adversarial training method that enhances the trade-off between standard and robust generalization while also mitigating robust overfitting.
In the paper "The Effectiveness of Random Forgetting for Robust Generalization", Vijaya Raghavan T Ramkumar, Bahram Zonooz, and Elahe Arani propose a method that alternates between the forgetting phase, which randomly forgets a subset of weights and regulates the model's information through weight reinitialization, and the relearning phase, which mitigate robust overfitting.In the paper "Task Adaptation from Skills: Information Geometry, Disentanglement, and New Objectives for Unsupervised Reinforcement Learning", Yucheng Yang, Tianyi Zhou, Qiang He, Lei Han, Mykola Pechenizkiy, and Meng Fang propose a novel disentanglement metric LSEPIN and build an information-geometric connection between LSEPIN and downstream task adaptation cost in an unsupervised reinforcement learning setting.
External
-
Joaquin Vanschoren chair of the MLCommons AI Safety working group
Joaquin Vanschoren became a chair of the MLCommons AI Safety working group, together with Percy Liang (Stanford) and Peter Mattseon (Google). You can join too! Follow the link for more information.
External
Collaboration with Honda Research Institute
The paper Towards Probabilistic Clearance, Explanation and Optimization by Simon Kohaut, Benedict Flade, Devendra Singh Dhami, Julian Eggert and Kristian Kersting in collaboration with the Honda Research Institute has been accepted at the International Conference on Unmanned Aircraft Systems (ICUAS)
Multiple articles accepted at machine learning journals
Enhancing performance of vision transformers on small datasets through local inductive bias incorporation by Ibrahim Batuhan Akkaya, Senthilkumar S. Kathiresan, Elahe Arani, and Bahram Zonooz has been published at the Pattern Recognition Journal IMEX-Reg: Implicit-Explicit Regularization in the Function Space for Continual Learning by Prashant Bhat, Bharath Renjith, Elahe Arani, and Bahram Zonooz has been published at Transactions on Machine Learning ResearchAMLB: an AutoML Benchmark by Pieter Gijsbers, Marcos L. P. Bueno, Stefan Coors, Erin LeDell, Sébastien Poirier, Janek Thomas, Bernd Bischl, and Joaquin Vanschoren has been published at Journal of Machine Learning ResearchMachine Learning meets Kepler: Inverting Kepler’s Equation for All vs All Conjunction Analysis by Kevin Otto, Simon Burgis, Kristian Kersting, Reinhold Bertrand, and Devendra Singh Dhami has been published in Machine Learning: Science and Technology (MLST)Neuro-Symbolic Predicate Invention: Learning Relational Concepts from Visual Scenes by Jingyuan Sha, Hikaru Shindo, Kristian Kersting, and Devendra Singh Dhami has been published in Neurosymbolic Artificial Intelligence
Multiple papers have been accepted at CoLLAs 2024
The following papers will be presented at the Third Conference on Lifelong Learning Agents:Beyond Unimodal Learning: The Importance of Integrating Multiple Modalities for Lifelong Learning by Fahad Sarfraz, Bahram Zonooz, Elahe AraniMitigating Interference in the Knowledge Continuum through Attention-Guided Incremental Learning by Prashant Bhat, Bharath Renjith, Elahe Arani, Bahram ZonoozLearning to learn without forgetting using attention by Anna Vettoruzzo, Joaquin Vanschoren, Mohamed-Rafik Bouguelia, and Thorsteinn S. Rögnvaldsson
External
Multiple papers accepted at ICML 2024
Our cluster will be greatly represented at ICML! The following papers will be presented in Vienna: Provably Efficient Exploration in Constrained Reinforcement Learning: Posterior Sampling Is All You Need by Danil Provodin, Maurits Kaptein and Mykola Pechenizkiy.MALIBO: Meta-learning for Likelihood-free Bayesian Optimization by Jiarong Pan, Stefan Falkner, Felix Berkenkamp, and Joaquin VanschorenTrustLLM: Trustworthiness in Large Language Models by Lichao Sun et al. including Joaquin VanschorenScalable Safe Policy Improvement for Factored Multi-Agent MDPs by Federico Bianchi, Edoardo Zorzi, Alberto Castellini, Thiago D. Simão, Matthijs T. J. Spaan, and Alessandro FarinelliGradual Divergence for Seamless Adaptation: A Novel Domain Incremental Learning Method by Kishaan Jeeveswaran, Elahe Arani, and Bahram ZonoozCongratulations to all of our amazing researchers who have submitted their work to this top-tier conference!
External
Two works to be presented at ICDE'24 and MulTiSA'24 (co-located with ICDE)
Join us at ICDE to hear a lightning talk titled "Multivariate similarity search - a call for a new breed of similarity search algorithms" and a workshop talk at MulTiSA'24 titled "Beyond the Dimensions: A Structured Evaluation of Multivariate Time Series Distance Measures" by our Database group colleagues, Odysseas Papapetrou and Jens d'Hondt.
External
A workshop at ICDE'24
Our member, Odysseas Papapetrou, is organizing the first Multivariate Time Series Analytics workshop (MulTiSA'24), at ICDE'24. It is not too late to register and join us, to hear about the state of the art on multivariate time series.
External
PhD position with the Database group on data streams
The Database group has a 5-years PhD vacancy on synopses for data stream processing. Have a look here for more details and for instructions to apply: https://jobs.tue.nl/en/vacancy/phd-on-streaming-data-management-1078132.htmlWe will be at ICDE'24 in Utrecht. If you are there and want to have an informal chat about this position, send us an email at o.papapetrou@tue.nl
External
ICML 2024 GRaM workshop (July)
Our member Jakub Tomczak is co-organizing the first edition of GRaM: Geometry-grounded Representation Learning and Generative Modeling Workshop at ICML 2024 in Vienna, Austria.
For more info, see the link.
External
Two papers accepted at UAI 2024
In the paper "Pix2Code: Learning to Compose Neural Visual Concepts as Programs", Antonia Wüst, Wolfgang Stammer, Quentin Delfosse, Devendra Singh Dhami, and Kristian Kersting propose Pix2Code, a framework that extends program synthesis to visual relational reasoning by utilizing the abilities of explicit, compositional symbolic and implicit neural representations.In the paper chiSPN: Characteristic Interventional Sum-Product Networks for Causal Inference in Hybrid Domains, Harsh Poonia, Moritz Willig, Zhongjie Yu, Matej Zečević, Kristian Kersting, and Devendra Singh Dhami extend sum-product networks for causal inference to hybrid domain i.e. domain with heterogeneous data. chiSPN provides a unified view for discrete and continuous random variables through the Fourier–Stieltjes transform of the probability measures thereby making it possible to do causal inference from both types of data at once.
External
Workshop on Explainable AI (23/05)
The ELA AI Triangle (EAISI, Leuven.AI, and RWTH AI Center) Workshop series on Explainable AI will kick off on May 23rd at TU Eindhoven.
The first workshop in the series will focus on theories, methods,
and applications of (neuro-) symbolic AI that enable and/or leverage
explainability.
However, all researchers interested in this and other XAI
subareas are welcome to attend and contribute. Registration is free! See link for more info.
External
Mini-symposium "Is knowledge useful?" (19/04)
On April 19th we will hold a mini-symposium titled "Is knowledge useful?". We will discuss how to represent knowledge, and when and how to use it for different applications. See link for details of the event!
External
Colloquium on uncertainties in AI (Feb 5th)
On Feb 5 the UAI group is organizing a colloquium on uncertainties in AI, together with partners at TU/e, RWTH Aachen Uni & KU Leuven. The event is held at MetaForum 4.208, 15:45-17:15, and open to everyone! See link for more info
External
Two papers accepted at AISTATS 2024
In the paper "Probabilistic Integral Circuits", Gennaro Gala, Cassio de Campos, Robert Peharz, Antonio Vergari, and Erik Quaeghebeur show how to represent and perform inference on continuous latent variable models in the language of circuits.In the paper "Attention-based Multi-instance Mixed Models", Jan P. Engelmann, Alessandro Palma, Jakub M. Tomczak, Fabian J Theis, and Francesco Paolo Casale present GMIL, a framework integrating Generalized Linear Mixed Models (GLMM) and Multiple Instance Learning (MIL), that upholds the advantages of linear models while modeling data heterogeneity uisng pre-defined embeddings.
External
Four papers accepted at ICLR 2024
In the paper "Learning Large DAGs is Harder than you Think: Many Losses are Minimal for the Wrong DAG", Jonas Seng, Matej Zečević, Devendra Singh Dhami, and Kristian Kersting consider the structure learning problem, which is hard for even simple DAG’s. They formally proved that measurement scale can decide which DAGs will minimize the MMSE or log-likelihood based losses such as ELBO and BIC and thus should be treated with care.
In the paper "Conserve-Update-Revise to Cure Generalization and Robustness Trade-off in Adversarial Training", Shruthi Gowda, Bahram Zonooz, and Elahe Arani propose a selective adversarial training method that enhances the trade-off between standard and robust generalization while also mitigating robust overfitting.
In the paper "The Effectiveness of Random Forgetting for Robust Generalization", Vijaya Raghavan T Ramkumar, Bahram Zonooz, and Elahe Arani propose a method that alternates between the forgetting phase, which randomly forgets a subset of weights and regulates the model's information through weight reinitialization, and the relearning phase, which mitigate robust overfitting.In the paper "Task Adaptation from Skills: Information Geometry, Disentanglement, and New Objectives for Unsupervised Reinforcement Learning", Yucheng Yang, Tianyi Zhou, Qiang He, Lei Han, Mykola Pechenizkiy, and Meng Fang propose a novel disentanglement metric LSEPIN and build an information-geometric connection between LSEPIN and downstream task adaptation cost in an unsupervised reinforcement learning setting.
External
Joaquin Vanschoren chair of the MLCommons AI Safety working group
Joaquin Vanschoren became a chair of the MLCommons AI Safety working group, together with Percy Liang (Stanford) and Peter Mattseon (Google). You can join too! Follow the link for more information.
External