Search Results for author:
Found 53 papers, 19 papers with code
AI Competitions and Benchmarks: Dataset Development
Initially, we develop the tasks involved in dataset development and offer insights into their effective management (including requirements, design, implementation, evaluation, distribution, and maintenance).
Unified Physical-Digital Attack Detection Challenge
Based on this dataset, we organized a Unified Physical-Digital Face Attack Detection Challenge to boost the research in Unified Attack Detections.
Challenge design roadmap
However, these rules have multiple objectives beyond making the game enjoyable for participants.
DMLR: Data-centric Machine Learning Research -- Past, Present and Future
Drawing from discussions at the inaugural DMLR workshop at ICML 2023 and meetings prior, in this report we outline the relevance of community engagement and infrastructure development for the creation of next-generation public datasets that will advance machine learning science.
Modularity in Deep Learning: A Survey
We review the notion of modularity in deep learning around three axes: data, task, and model, which characterize the life cycle of deep learning.
RRR-Net: Reusing, Reducing, and Recycling a Deep Backbone Network
It has become mainstream in computer vision and other machine learning domains to reuse backbone networks pre-trained on large datasets as preprocessors.
Is One Epoch All You Need For Multi-Fidelity Hyperparameter Optimization?
Hyperparameter optimization (HPO) is crucial for fine-tuning machine learning models but can be computationally expensive.
Meta-Album: Multi-domain Meta-Dataset for Few-Shot Image Classification
We introduce Meta-Album, an image classification meta-dataset designed to facilitate few-shot learning, transfer learning, meta-learning, among other tasks.
NeurIPS'22 Cross-Domain MetaDL competition: Design and baseline results
We present the design and baseline results for a new challenge in the ChaLearn meta-learning series, accepted at NeurIPS'22, focusing on "cross-domain" meta-learning.
Meta-learning from Learning Curves Challenge: Lessons learned from the First Round and Design of the Second Round
With the lessons learned from the first round and the feedback from the participants, we have designed the second round of our challenge with a new protocol and a new meta-dataset.
Reinforcement learning for Energies of the future and carbon neutrality: a Challenge Design
Current rapid changes in climate increase the urgency to change energy production and consumption management, to reduce carbon and other green-house gas production.
Asynchronous Decentralized Bayesian Optimization for Large Scale Hyperparameter Optimization
Bayesian optimization (BO) is a promising approach for hyperparameter optimization of deep neural networks (DNNs), where each model training can take minutes to hours.
Lessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classification
Although deep neural networks are capable of achieving performance superior to humans on various tasks, they are notorious for requiring large amounts of data and computing resources, restricting their success to domains where such resources are available.
Bridging the Gap of AutoGraph between Academia and Industry: Analysing AutoGraph Challenge at KDD Cup 2020
Researchers naturally adopt Automated Machine Learning on Graph Learning, aiming to reduce the human effort and achieve generally top-performing GNNs, but their methods focus more on the architecture search.
Comparison of Spatio-Temporal Models for Human Motion and Pose Forecasting in Face-to-Face Interaction Scenarios
In this work, we present the first systematic comparison of state-of-the-art approaches for behavior forecasting.
Didn't see that coming: a survey on non-verbal social human behavior forecasting
Non-verbal social human behavior forecasting has increasingly attracted the interest of the research community in recent years.
Learning by Doing: Controlling a Dynamical System using Causality, Control, and Reinforcement Learning
Questions in causality, control, and reinforcement learning go beyond the classical machine learning task of prediction under i. i. d.
Model-based Reinforcement Learning
reinforcement-learning
+1
LTU Attacker for Membership Inference
In both cases classification accuracy or error rate are used as the metric: Utility is evaluated with the classification accuracy of the Defender model; Privacy is evaluated with the membership prediction error of a so-called "Leave-Two-Unlabeled" LTU Attacker, having access to all of the Defender and Reserved data, except for the membership label of one sample from each.
Advances in MetaDL: AAAI 2021 challenge and workshop
Winning methods featured various classifiers trained on top of the second last layer of popular CNN backbones, fined-tuned on the meta-training data (not necessarily in an episodic manner), then trained on the labeled support and tested on the unlabeled query sets of the meta-test data.
OmniPrint: A Configurable Printed Character Synthesizer
We introduce OmniPrint, a synthetic data generator of isolated printed characters, geared toward machine learning research.
Winning solutions and post-challenge analyses of the ChaLearn AutoDL challenge 2019
Code submissions were executed on hidden tasks, with limited time and computational resources, pushing solutions that get results quickly.
AutoDEUQ: Automated Deep Ensemble with Uncertainty Quantification
However, building ensembles of neural networks is a challenging task because, in addition to choosing the right neural architecture or hyperparameters for each member of the ensemble, there is an added cost of training each model.
Codabench: Flexible, Easy-to-Use and Reproducible Benchmarking Platform
A public instance of Codabench (https://www. codabench. org/) is open to everyone, free of charge, and allows benchmark organizers to compare fairly submissions, under the same setting (software, hardware, data, algorithms), with custom protocols and data formats.
AutoML Meets Time Series Regression Design and Analysis of the AutoSeries Challenge
Driven by business scenarios, we organized the first Automated Time Series Regression challenge (AutoSeries) for the WSDM Cup 2020.
ChaLearn Looking at People: Inpainting and Denoising challenges
Dealing with incomplete information is a well studied problem in the context of machine learning and computational intelligence.
The Tracking Machine Learning challenge : Throughput phase
Both were measured on the Codalab platform where the participants had to upload their software.
Bayesian Optimization is Superior to Random Search for Machine Learning Hyperparameter Tuning: Analysis of the Black-Box Optimization Challenge 2020
It was based on tuning (validation set) performance of standard machine learning models on real datasets.
Learning to run a Power Network Challenge: a Retrospective Analysis
Motivated to investigate the potential of AI methods in enabling adaptability in power network operation, we have designed a L2RPN challenge to encourage the development of reinforcement learning solutions to key problems present in the next-generation power networks.
NeurIPS 2020 Competition: Predicting Generalization in Deep Learning
Understanding generalization in deep learning is arguably one of the most important questions in deep learning.
Deep Statistical Solvers
This paper introduces Deep Statistical Solvers (DSS), a new class of trainable solvers for optimization problems, arising e. g., from system simulations.
AgEBO-Tabular: Joint Neural Architecture and Hyperparameter Search with Autotuned Data-Parallel Training for Tabular Data
Neural architecture search (NAS) is an AutoML approach that generates and evaluates multiple neural network architectures concurrently and improves the accuracy of the generated models iteratively.
Learning to run a power network challenge for training topology controllers
For power grid operations, a large body of research focuses on using generation redispatching, load shedding or demand side management flexibilities.
Synthetic Event Time Series Health Data Generation
Due to the complexity of the real data, in which each patient visit is an event, we transform the data by using summary statistics to characterize the events for a fixed set of time intervals, to facilitate analysis and interpretability.
LEAP nets for power grid perturbations
We propose a novel neural network embedding approach to model power transmission grids, in which high voltage lines are disconnected and reconnected with one-another from time to time, either accidentally or willfully.
ChaLearn Looking at People: IsoGD and ConGD Large-scale RGB-D Gesture Recognition
The ChaLearn large-scale gesture recognition challenge has been run twice in two workshops in conjunction with the International Conference on Pattern Recognition (ICPR) 2016 and International Conference on Computer Vision (ICCV) 2017, attracting more than $200$ teams round the world.
Towards AutoML in the presence of Drift: first results
We extendAuto-Sklearn with sound and intuitive mechanisms that allow it to cope with this sort ofproblems.
Graph Neural Solver for Power Systems
Load flow computation is a well studied and understood problem, but current methods (based on Newton-Raphson) are slow.
Analysis of the AutoML Challenge Series 2015–2018
The solutions of the winners are systematically benchmarked over all datasets of all rounds and compared with canonical machine learning algorithms available in scikit-learn.
Ranked #1 on
AutoML
on Chalearn-AutoML-1
AutoML @ NeurIPS 2018 challenge: Design and Results
We organized a competition on Autonomous Lifelong Machine Learning with Drift that was part of the competition program of NeurIPS 2018.
Lessons learned from the AutoML challenge
We give a brief account of the main findings of our post-hoc analysis of the first AutoML challenge (2015-2016).
Optimization of computational budget for power system risk assessment
We address the problem of maintaining high voltage power transmission networks in security at all time, namely anticipating exceeding of thermal limit for eventual single line disconnection (whatever its cause may be) by running slow, but accurate, physical grid simulators.
Anticipating contingengies in power grids using fast neural net screening
We evaluate that our method scales up to power grids of the size of the French high voltage power grid (over 1000 power lines).
First Impressions: A Survey on Vision-Based Apparent Personality Trait Analysis
However, recently there has been an increasing interest from the computer vision community in analyzing personality from visual data.
Structural Agnostic Modeling: Adversarial Learning of Causal Graphs
A new causal discovery method, Structural Agnostic Modeling (SAM), is presented in this paper.
Explaining First Impressions: Modeling, Recognizing, and Explaining Apparent Personality from Videos
Explainability and interpretability are two critical aspects of decision support systems.
Fast Power system security analysis with Guided Dropout
We propose a new method to efficiently compute load-flows (the steady-state of the power-grid for given productions, consumptions and grid topology), substituting conventional simulators based on differential equation solvers.
Causal Generative Neural Networks
We present Causal Generative Neural Networks (CGNNs) to learn functional causal models from observational data.
Introducing machine learning for power system operation support
One of the primary goals of dispatchers is to protect equipment (e. g. avoid that transmission lines overheat) with few degrees of freedom: we are considering in this paper solely modifications in network topology, i. e. re-configuring the way in which lines, transformers, productions and loads are connected in sub-stations.
Learning Functional Causal Models with Generative Neural Networks
We introduce a new approach to functional causal modeling from observational data, called Causal Generative Neural Networks (CGNN).
Design and Analysis of the NIPS 2016 Review Process
Neural Information Processing Systems (NIPS) is a top-tier annual conference in machine learning.
ChaLearn Looking at People: A Review of Events and Resources
This paper reviews associated events, and introduces the ChaLearn LAP platform where public resources (including code, data and preprints of papers) related to the organized events are available.
ChaLearn Looking at People and Faces of the World: Face Analysis Workshop and Challenge 2016
A custom-build application was used to collect and label data about the apparent age of people (as opposed to the real age).
Ranked #2 on
Gender Prediction
on FotW Gender
Principal motion components for gesture recognition using a single-example
In the considered scenario a single training-video is available for each gesture to be recognized, which limits the application of traditional techniques (e. g., HMMs).
