Search Results for author: Jean Kaddour

Found 10 papers, 6 papers with code

The MiniPile Challenge for Data-Efficient Language Models

no code implementations17 Apr 2023 Jean Kaddour

MiniPile is a 6GB subset of the deduplicated 825GB The Pile corpus.

Language Modelling

Spawrious: A Benchmark for Fine Control of Spurious Correlation Biases

1 code implementation9 Mar 2023 Aengus Lynch, Gbètondji J-S Dovonon, Jean Kaddour, Ricardo Silva

The problem of spurious correlations (SCs) arises when a classifier relies on non-predictive features that happen to be correlated with the labels in the training data.

Image Captioning Image Classification

DAG Learning on the Permutahedron

1 code implementation27 Jan 2023 Valentina Zantedeschi, Luca Franceschi, Jean Kaddour, Matt J. Kusner, Vlad Niculae

We propose a continuous optimization framework for discovering a latent directed acyclic graph (DAG) from observational data.

Stop Wasting My Time! Saving Days of ImageNet and BERT Training with Latest Weight Averaging

1 code implementation29 Sep 2022 Jean Kaddour

Training vision or language models on large datasets can take days, if not weeks.

Causal Machine Learning: A Survey and Open Problems

no code implementations30 Jun 2022 Jean Kaddour, Aengus Lynch, Qi Liu, Matt J. Kusner, Ricardo Silva

Causal Machine Learning (CausalML) is an umbrella term for machine learning methods that formalize the data-generation process as a structural causal model (SCM).

BIG-bench Machine Learning Fairness +1

Evaluating Self-Supervised Learning for Molecular Graph Embeddings

no code implementations16 Jun 2022 Hanchen Wang, Jean Kaddour, Shengchao Liu, Jian Tang, Matt Kusner, Joan Lasenby, Qi Liu

Graph Self-Supervised Learning (GSSL) paves the way for learning graph embeddings without expert annotation, which is particularly impactful for molecular graphs since the number of possible molecules is enormous and labels are expensive to obtain.

Benchmarking Management +1

When Do Flat Minima Optimizers Work?

1 code implementation1 Feb 2022 Jean Kaddour, Linqing Liu, Ricardo Silva, Matt J. Kusner

Recently, flat-minima optimizers, which seek to find parameters in low-loss neighborhoods, have been shown to improve a neural network's generalization performance over stochastic and adaptive gradient-based optimizers.

Benchmarking Graph Learning +9

Causal Effect Inference for Structured Treatments

2 code implementations NeurIPS 2021 Jean Kaddour, Yuchen Zhu, Qi Liu, Matt J. Kusner, Ricardo Silva

We address the estimation of conditional average treatment effects (CATEs) for structured treatments (e. g., graphs, images, texts).

Probabilistic Active Meta-Learning

1 code implementation NeurIPS 2020 Jean Kaddour, Steindór Sæmundsson, Marc Peter Deisenroth

However, this setting does not take into account the sequential nature that naturally arises when training a model from scratch in real-life: how do we collect a set of training tasks in a data-efficient manner?


Cannot find the paper you are looking for? You can Submit a new open access paper.