Emergent multi-agent communication in the deep learning era

A Lazaridou, M Baroni - arxiv preprint arxiv:2006.02419, 2020 - arxiv.org
The ability to cooperate through language is a defining feature of humans. As the
perceptual, motory and planning capabilities of deep artificial networks increase …

[HTML][HTML] Learning disentangled representations in the imaging domain

X Liu, P Sanchez, S Thermos, AQ O'Neil… - Medical Image …, 2022 - Elsevier
Disentangled representation learning has been proposed as an approach to learning
general representations even in the absence of, or with limited, supervision. A good general …

Toward causal representation learning

B Schölkopf, F Locatello, S Bauer, NR Ke… - Proceedings of the …, 2021 - ieeexplore.ieee.org
The two fields of machine learning and graphical causality arose and are developed
separately. However, there is, now, cross-pollination and increasing interest in both fields to …

Disentangled representation learning

X Wang, H Chen, Z Wu, W Zhu - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Disentangled Representation Learning (DRL) aims to learn a model capable of identifying
and disentangling the underlying factors hidden in the observable data in representation …

Self-supervised learning with data augmentations provably isolates content from style

J Von Kügelgen, Y Sharma, L Gresele… - Advances in neural …, 2021 - proceedings.neurips.cc
Self-supervised representation learning has shown remarkable success in a number of
domains. A common practice is to perform data augmentation via hand-crafted …

Causal intervention for weakly-supervised semantic segmentation

D Zhang, H Zhang, J Tang… - Advances in Neural …, 2020 - proceedings.neurips.cc
We present a causal inference framework to improve Weakly-Supervised Semantic
Segmentation (WSSS). Specifically, we aim to generate better pixel-level pseudo-masks by …

Causality for machine learning

B Schölkopf - Probabilistic and causal inference: The works of Judea …, 2022 - dl.acm.org
The machine learning community's interest in causality has significantly increased in recent
years. My understanding of causality has been shaped by Judea Pearl and a number of …

Counterfactual zero-shot and open-set visual recognition

Z Yue, T Wang, Q Sun, XS Hua… - Proceedings of the …, 2021 - openaccess.thecvf.com
We present a novel counterfactual framework for both Zero-Shot Learning (ZSL) and Open-
Set Recognition (OSR), whose common challenge is generalizing to the unseen-classes by …

Interventional few-shot learning

Z Yue, H Zhang, Q Sun, XS Hua - Advances in neural …, 2020 - proceedings.neurips.cc
We uncover an ever-overlooked deficiency in the prevailing Few-Shot Learning (FSL)
methods: the pre-trained knowledge is indeed a confounder that limits the performance. This …

Disentangling user interest and conformity for recommendation with causal embedding

Y Zheng, C Gao, X Li, X He, Y Li, D ** - Proceedings of the Web …, 2021 - dl.acm.org
Recommendation models are usually trained on observational interaction data. However,
observational interaction data could result from users' conformity towards popular items …