Publications

Physics-Informed Transformer Networks

Fabricio Dos Santos

F. Dos

Tara Akhound-Sadegh

Siamak Ravanbakhsh

Physics-informed neural networks (PINNs) have been recognized as a viable alternative to conventional numerical solvers for Partial Differen… (see more)tial Equations (PDEs). The main appeal of PINNs is that since they directly enforce the PDE equation, one does not require access to costly ground truth solutions for training the model. However, a key challenge is their limited generalization across varied initial conditions. Addressing this, our study presents a novel Physics-Informed Transformer (PIT) model for learning the solution operator for PDEs. Using the attention mechanism, PIT learns to leverage the relationships between its initial condition and query points, resulting in a significant improvement in generalization. Moreover, in contrast to existing physics-informed networks, our model is invariant to the discretization of the input domain, providing great flexibility in problem specification and training. We validated our proposed method on the 1D Burgers’ and the 2D Heat equations, demonstrating notable improvement over standard PINN models for operator learning with negligible computational overhead.

2023-10-31

NeurIPS.cc/2023/Workshop/DLDE (poster)

Root phosphatase activity is coordinated with the root conservation gradient across a phosphorus gradient in a lowland tropical forest

Xavier Guilbeault-Mayers

Étienne Laliberté

Soil phosphorus (P) is a growth-limiting nutrient in tropical ecosystems, driving diverse P-acquisition strategies among plants. Particularl… (see more)y, mining for inorganic P through phosphomonoesterase (PME) activity is essential, given the substantial proportion of organic P in soils. Yet the relationship between PME activity and other P-acquisition root traits remains unclear. We measured root PME activity and commonly-measured root traits, including root diameter, specific root length (SRL), root tissue density (RTD), and nitrogen concentration ([N]) in 18 co-occurring trees across soils with varying P availability to better understand trees response to P supply. Root [N] and RTD were inversely related, and that axis was related to soil P supply. Indeed, both traits correlated positively and negatively to PME activity, which responded strongly to P supply. Conversely, root diameter was inversely related to SRL, but this axis was not related to P supply. Suggesting that limiting similarity influenced variation along the diameter-SRL axis, explaining high local trait diversity. Meanwhile, environmental filtering tended to impact trait values along the root [N]-RTD axis. Overall, P availability indicator traits like PME activity and root hairs only tended to be associated with these axes, highlighting limitations of these axes in describing convergent adaptations at local sites.

2023-10-31

bioRxiv (preprint)

Causal Fair Metric: Bridging Causality, Individual Fairness, and Adversarial Robustness

Ahmad-reza Ehyaei

Golnoosh Farnadi

Samira Samadi

Despite the essential need for comprehensive considerations in responsible AI, factors like robustness, fairness, and causality are often st… (see more)udied in isolation. Adversarial perturbation, used to identify vulnerabilities in models, and individual fairness, aiming for equitable treatment of similar individuals, despite initial differences, both depend on metrics to generate comparable input data instances. Previous attempts to define such joint metrics often lack general assumptions about data or structural causal models and were unable to reflect counterfactual proximity. To address this, our paper introduces a causal fair metric formulated based on causal structures encompassing sensitive attributes and protected causal perturbation. To enhance the practicality of our metric, we propose metric learning as a method for metric estimation and deployment in real-world problems in the absence of structural causal models. We also demonstrate the application of our novel metric in classifiers. Empirical evaluation of real-world and synthetic datasets illustrates the effectiveness of our proposed metric in achieving an accurate classifier with fairness, resilience to adversarial perturbations, and a nuanced understanding of causal relationships.

2023-10-30

ArXiv (preprint)

Characterizing Manipulation from AI Systems

Micah Carroll

Alan Chan

Henry Ashton

David Scott Krueger

Manipulation is a concern in many domains, such as social media, advertising, and chatbots. As AI systems mediate more of our digital intera… (see more)ctions, it is important to understand the degree to which AI systems might manipulate humans without the intent of the system designers. Our work clarifies challenges in defining and measuring this kind of manipulation from AI systems. Firstly, we build upon prior literature on manipulation and characterize the space of possible notions of manipulation, which we find to depend upon the concepts of incentives, intent, covertness, and harm. We review proposals on how to operationalize each concept and we outline challenges in including each concept in a definition of manipulation. Second, we discuss the connections between manipulation and related concepts, such as deception and coercion. We then analyze how our characterization of manipulation applies to recommender systems and language models, and give a brief overview of the regulation of manipulation in other domains. While some progress has been made in defining and measuring manipulation from AI systems, many gaps remain. In the absence of a consensus definition and reliable tools for measurement, we cannot rule out the possibility that AI systems learn to manipulate humans without the intent of the system designers. Manipulation could pose a significant threat to human autonomy and precautionary actions to mitigate it are likely warranted.

2023-10-30

Equity and Access in Algorithms, Mechanisms, and Optimization (published)

FETA: Fairness Enforced Verifying, Training, and Predicting Algorithms for Neural Networks

Kiarash Mohammadi

Aishwarya Sivaraman

Golnoosh Farnadi

2023-10-30

Equity and Access in Algorithms, Mechanisms, and Optimization (published)

TorchProbe: Fuzzing Dynamic Deep Learning Compilers

Qidong Su

Chuqin Geng

Gennady G. Pekhimenko

Xujie Si

Static and dynamic computational graphs represent two distinct approaches to constructing deep learning frameworks. The former prioritizes c… (see more)ompiler-based optimizations, while the latter focuses on programmability and user-friendliness. The recent release of PyTorch 2.0, which supports compiling arbitrary deep learning programs in Python, signifies a new direction in the evolution of deep learning infrastructure to incorporate compiler techniques in a more dynamic manner and support more dynamic language features like dynamic control flows and closures. Given PyTorch's seamless integration with Python, its compiler aims to support arbitrary deep learning code written in Python. However, the inherent dynamism of Python poses challenges to the completeness and robustness of the compiler. While recent research has introduced fuzzing to test deep learning compilers, there is still a lack of comprehensive analysis on how to test dynamic features. To address this issue, we propose several code transformations to generate test cases involving dynamic features. These transformations preserve the program's semantics, ensuring that any discrepancy between the transformed and original programs indicates the presence of a bug. Through our approach, we have successfully identified twenty previously unknown bugs in the PyTorch compiler and its underlying tensor compiler Triton.

2023-10-30

ArXiv (preprint)

Unraveling the Interconnected Axes of Heterogeneity in Machine Learning for Democratic and Inclusive Advancements

Maryam Molamohammadi

Afaf Taïk

Nicolas Le Roux

Golnoosh Farnadi

2023-10-30

Equity and Access in Algorithms, Mechanisms, and Optimization (published)

Proving Linear Mode Connectivity of Neural Networks via Optimal Transport

Damien Ferbach

Baptiste Goujaud

Gauthier Gidel

Aymeric Dieuleveut

The energy landscape of high-dimensional non-convex optimization problems is crucial to understanding the effectiveness of modern deep neura… (see more)l network architectures. Recent works have experimentally shown that two different solutions found after two runs of a stochastic training are often connected by very simple continuous paths (e.g., linear) modulo a permutation of the weights. In this paper, we provide a framework theoretically explaining this empirical observation. Based on convergence rates in Wasserstein distance of empirical measures, we show that, with high probability, two wide enough two-layer neural networks trained with stochastic gradient descent are linearly connected. Additionally, we express upper and lower bounds on the width of each layer of two deep neural networks with independent neuron weights to be linearly connected. Finally, we empirically demonstrate the validity of our approach by showing how the dimension of the support of the weight distribution of neurons, which dictates Wasserstein convergence rates is correlated with linear mode connectivity.

2023-10-29

ArXiv (preprint)

A Case Study of Instruction Tuning with Mixture of Parameter-Efficient Experts

Oleksiy Ostapenko

Lucas Caccia

Zhan Su

Nicolas Le Roux

Laurent Charlin

Alessandro Sordoni

We study the applicability of mixture of parameter-efficient experts (MoPEs) for instruction-tuning large decoder-only language models. Rece… (see more)nt literature indicates that MoPEs might enhance performance in specific multi-task instruction-following datasets. In this paper, we extend such previous results and study applicability of MoPEs in settings previously overlooked: a) with open-domain instruction-following datasets; b) with recent decoder-only models and c) with downstream out-of-distribution test sets. We build on top of LLaMA1-13B/-7B and LLaMA2-13B. We study different variants of learned routing, namely per-example routing ([PE]), and a more expensive per-token ([PT]) routing. Overall, we are unable to substantiate strong performance gains observed in related studies in our setting. We observe occasional enhancements of LLAMA2 fine-tuned on Open Platypus dataset in 0-shot SNI evaluation and TruthfulQA evaluation after fine-tuning on a subset of Flan. We shed some light on the inner workings of MoPEs by comparing different routing strategies. We find that [PE] routing tends to collapse at downstream evaluation time reducing the importance of router's application. We plan to publicly release our code.

2023-10-28

NeurIPS.cc/2023/Workshop/Instruction (published)

Detecting Backdoors with Meta-Models

Lauro Langosco

Neel Alex

William Baker

David John Quarel

Herbie Bradley

David Scott Krueger

It is widely known that it is possible to implant backdoors into neural networks, by which an attacker can choose an input to produce a part… (see more)icular undesirable output (e.g.\ misclassify an image). We propose to use \emph{meta-models}, neural networks that take another network's parameters as input, to detect backdoors directly from model weights. To this end we present a meta-model architecture and train it on a dataset of approx.\ 4000 clean and backdoored CNNs trained on CIFAR-10. Our approach is simple and scalable, and is able to detect the presence of a backdoor with

2023-10-28

NeurIPS.cc/2023/Workshop/BUGS (poster)

Detecting Backdoors with Meta-Models

Lauro Langosco

Neel Alex

William Baker

David John Quarel

Herbie Bradley

David Scott Krueger

It is widely known that it is possible to implant backdoors into neural networks, by which an attacker can choose an input to produce a part… (see more)icular undesirable output (e.g.\ misclassify an image). We propose to use \emph{meta-models}, neural networks that take another network's parameters as input, to detect backdoors directly from model weights. To this end we present a meta-model architecture and train it on a dataset of approx.\ 4000 clean and backdoored CNNs trained on CIFAR-10. Our approach is simple and scalable, and is able to detect the presence of a backdoor with

2023-10-28

NeurIPS.cc/2023/Workshop/BUGS (poster)