Publications

Leveraging Diffusion Disentangled Representations to Mitigate Shortcuts in Underspecified Visual Tasks
Luca Scimeca
Alexander Rubinstein
Armand Mihai Nicolicioiu
Damien Teney
Yoshua Bengio
Spurious correlations in the data, where multiple cues are predictive of the target labels, often lead to shortcut learning phenomena, where… (voir plus) a model may rely on erroneous, easy-to-learn, cues while ignoring reliable ones. In this work, we propose an ensemble diversification framework exploiting the generation of synthetic counterfactuals using Diffusion Probabilistic Models (DPMs). We discover that DPMs have the inherent capability to represent multiple visual cues independently, even when they are largely correlated in the training data. We leverage this characteristic to encourage model diversity and empirically show the efficacy of the approach with respect to several diversification objectives. We show that diffusion-guided diversification can lead models to avert attention from shortcut cues, achieving ensemble diversity performance comparable to previous methods requiring additional data collection.
2023-10-03
ArXiv (prépublication)
doi.org
arxiv.org
Aberrant functional brain network organization is associated with relapse during 1‐year follow‐up in alcohol‐dependent patients
Justin Böhmer
Pablo Reinhardt
Maria Garbusow
Michael Marxen
Michael N. Smolka
Ulrich S. Zimmermann
Andreas Heinz
Danilo Bzdok
Eva Friedel
Johann D. Kruschwitz
Henrik Walter
2023-10-02
Addiction Biology (publié)
doi.org
GraphText: Graph Reasoning in Text Space
Jianan Zhao
Le Zhuo
Yikang Shen
Meng Qu
Kai Liu
Michael Bronstein
Zhaocheng Zhu
Jian Tang
Large Language Models (LLMs) have gained the ability to assimilate human knowledge and facilitate natural language interactions with both hu… (voir plus)mans and other LLMs. However, despite their impressive achievements, LLMs have not made significant advancements in the realm of graph machine learning. This limitation arises because graphs encapsulate distinct relational data, making it challenging to transform them into natural language that LLMs understand. In this paper, we bridge this gap with a novel framework, GraphText, that translates graphs into natural language. GraphText derives a graph-syntax tree for each graph that encapsulates both the node attributes and inter-node relationships. Traversal of the tree yields a graph text sequence, which is then processed by an LLM to treat graph tasks as text generation tasks. Notably, GraphText offers multiple advantages. It introduces training-free graph reasoning: even without training on graph data, GraphText with ChatGPT can achieve on par with, or even surpassing, the performance of supervised-trained graph neural networks through in-context learning (ICL). Furthermore, GraphText paves the way for interactive graph reasoning, allowing both humans and LLMs to communicate with the model seamlessly using natural language. These capabilities underscore the vast, yet-to-be-explored potential of LLMs in the domain of graph machine learning.
2023-10-02
ArXiv (prépublication)
doi.org
arxiv.org
TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Series
Arjun Ashok
Étienne Marcotte
Valentina Zantedeschi
Nicolas Chapados
Alexandre Drouin
We introduce a new model for multivariate probabilistic time series prediction, designed to flexibly address a range of tasks including fore… (voir plus)casting, interpolation, and their combinations. Building on copula theory, we propose a simplified objective for the recently-introduced transformer-based attentional copulas (TACTiS), wherein the number of distributional parameters now scales linearly with the number of variables instead of factorially. The new objective requires the introduction of a training curriculum, which goes hand-in-hand with necessary changes to the original architecture. We show that the resulting model has significantly better training dynamics and achieves state-of-the-art performance across diverse real-world forecasting tasks, while maintaining the flexibility of prior work, such as seamless handling of unaligned and unevenly-sampled time series. Code is made available at https://github.com/ServiceNow/TACTiS.
2023-10-02
ArXiv (prépublication)
doi.org
arxiv.org
AI and Catastrophic Risk
Yoshua Bengio
Abstract:Since OpenAI's release of the very large language models Chat-GPT and GPT-4, the potential dangers of AI have garnered widespread p… (voir plus)ublic attention. In this essay, the author reviews the threats to democracy posed by the possibility of "rogue AIs," dangerous and powerful AIs that would execute harmful goals, irrespective of whether the outcomes are intended by humans. To mitigate against the risk that rogue AIs present to democracy and geopolitical stability, the author argues that research into safe and defensive AIs should be conducted by a multilateral, international network of research laboratories.
2023-10-01
Journal of Democracy (publié)
doi.org
AI and Catastrophic Risk
Yoshua Bengio
2023-10-01
Journal of Democracy (publié)
doi.org
AI and Catastrophic Risk
Yoshua Bengio
2023-10-01
Journal of Democracy (publié)
doi.org
AI and Catastrophic Risk
Yoshua Bengio
2023-10-01
Journal of Democracy (publié)
doi.org
AI and Catastrophic Risk
Yoshua Bengio
Abstract:Since OpenAI's release of the very large language models Chat-GPT and GPT-4, the potential dangers of AI have garnered widespread p… (voir plus)ublic attention. In this essay, the author reviews the threats to democracy posed by the possibility of "rogue AIs," dangerous and powerful AIs that would execute harmful goals, irrespective of whether the outcomes are intended by humans. To mitigate against the risk that rogue AIs present to democracy and geopolitical stability, the author argues that research into safe and defensive AIs should be conducted by a multilateral, international network of research laboratories.
2023-10-01
Journal of Democracy (publié)
doi.org
AI and Catastrophic Risk
Yoshua Bengio
2023-10-01
Journal of Democracy (publié)
doi.org
AI and Catastrophic Risk
Yoshua Bengio
Abstract:Since OpenAI's release of the very large language models Chat-GPT and GPT-4, the potential dangers of AI have garnered widespread p… (voir plus)ublic attention. In this essay, the author reviews the threats to democracy posed by the possibility of "rogue AIs," dangerous and powerful AIs that would execute harmful goals, irrespective of whether the outcomes are intended by humans. To mitigate against the risk that rogue AIs present to democracy and geopolitical stability, the author argues that research into safe and defensive AIs should be conducted by a multilateral, international network of research laboratories.
2023-10-01
Journal of Democracy (publié)
doi.org
Bootstrapping Adaptive Human-Machine Interfaces with Offline Reinforcement Learning
Jensen Gao
Siddharth Reddy
Glen Berseth
Anca Dragan
Sergey Levine
Adaptive interfaces can help users perform sequential decision-making tasks like robotic teleoperation given noisy, high-dimensional command… (voir plus) signals (e.g., from a brain-computer interface). Recent advances in human-in-the-loop machine learning enable such systems to improve by interacting with users, but tend to be limited by the amount of data that they can collect from individual users in practice. In this paper, we propose a reinforcement learning algorithm to address this by training an interface to map raw command signals to actions using a combination of offline pre-training and online fine-tuning. To address the challenges posed by noisy command signals and sparse rewards, we develop a novel method for representing and inferring the user's long-term intent for a given trajectory. We primarily evaluate our method's ability to assist users who can only communicate through noisy, high-dimensional input channels through a user study in which 12 participants performed a simulated navigation task by using their eye gaze to modulate a 128-dimensional command signal from their webcam. The results show that our method enables successful goal navigation more often than a baseline directional interface, by learning to denoise user commands signals and provide shared autonomy assistance. We further evaluate on a simulated Sawyer pushing task with eye gaze control, and the Lunar Lander game with simulated user commands, and find that our method improves over baseline interfaces in these domains as well. Extensive ablation experiments with simulated user commands empirically motivate each component of our method.
2023-10-01
2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (publié)
doi.org
arxiv.org