Publications

Performative Prediction with Neural Networks

Mehrnaz Mofakhami

Performative prediction is a framework for learning models that influence the data they intend to predict. We focus on finding classifiers t… (see more)hat are performatively stable, i.e. optimal for the data distribution they induce. Standard convergence results for finding a performatively stable classifier with the method of repeated risk minimization assume that the data distribution is Lipschitz continuous to the model's parameters. Under this assumption, the loss must be strongly convex and smooth in these parameters; otherwise, the method will diverge for some problems. In this work, we instead assume that the data distribution is Lipschitz continuous with respect to the model's predictions, a more natural assumption for performative systems. As a result, we are able to significantly relax the assumptions on the loss function. In particular, we do not need to assume convexity with respect to the model's parameters. As an illustration, we introduce a resampling procedure that models realistic distribution shifts and show that it satisfies our assumptions. We support our theory by showing that one can learn performatively stable classifiers with neural networks making predictions about real data that shift according to our proposed procedure.

2023-01-01

AISTATS (published)

doi.org

openreview.net

Performative Prediction with Neural Networks

Mehrnaz Mofakhami

Ioannis Mitliagkas

Gauthier Gidel

2023-01-01

AISTATS (published)

doi.org

openreview.net

Physics-Guided Adversarial Machine Learning for Aircraft Systems Simulation

Houssem Ben Braiek

Thomas Reid

Foutse Khomh

In the context of aircraft system performance assessment, deep learning technologies allow us to quickly infer models from experimental meas… (see more)urements, with less detailed system knowledge than usually required by physics-based modeling. However, this inexpensive model development also comes with new challenges regarding model trustworthiness. This article presents a novel approach, physics-guided adversarial machine learning (ML), which improves the confidence over the physics consistency of the model. The approach performs, first, a physics-guided adversarial testing phase to search for test inputs revealing behavioral system inconsistencies, while still falling within the range of foreseeable operational conditions. Then, it proceeds with a physics-informed adversarial training to teach the model the system-related physics domain foreknowledge through iteratively reducing the unwanted output deviations on the previously uncovered counterexamples. Empirical evaluation on two aircraft system performance models shows the effectiveness of our adversarial ML approach in exposing physical inconsistencies of both the models and in improving their propensity to be consistent with physics domain knowledge.

2023-01-01

IEEE Transactions on Reliability (published)

doi.org

arxiv.org

Physics-Inspired Protein Encoder Pre-Training via Siamese Sequence-Structure Diffusion Trajectory Prediction

Zuobai Zhang

Minghao Xu

Aurelie Lozano

Vijil Chenthamarakshan

Payel Das

Jian Tang

Pre-training methods on proteins are recently gaining interest, leveraging either protein sequences or structures, while modeling their join… (see more)t energy landscape is largely unexplored. In this work, inspired by the success of denoising diffusion models, we propose the DiffPreT approach to pre-train a protein encoder by sequence-structure multimodal diffusion modeling. DiffPreT guides the encoder to recover the native protein sequences and structures from the perturbed ones along the multimodal diffusion trajectory, which acquires the joint distribution of sequences and structures. Considering the essential protein conformational variations, we enhance DiffPreT by a physics-inspired method called Siamese Diffusion Trajectory Prediction ( SiamDiff ) to capture the correlation between different conformers of a protein. SiamDiff attains this goal by maximizing the mutual information between representations of diffusion trajectories of structurally-correlated conformers. We study the effectiveness of DiffPreT and SiamDiff on both atom-and residue-level structure-based protein understanding tasks. Experimental results show that the performance of DiffPreT is consistently competitive on all tasks, and SiamDiff achieves new state-of-the-art performance, considering the mean ranks on all tasks. The source code will be released upon acceptance.

2023-01-01

arXiv.org (preprint)

doi.org

Preference-Based Offline Evaluation

C. Clarke

Fernando Diaz

Negar Arabzadeh

A core step in production model research and development involves the offline evaluation of a system before production deployment. Tradition… (see more)al offline evaluation of search, recommender, and other systems involves gathering item relevance labels from human editors. These labels can then be used to assess system performance using offline evaluation metrics. Unfortunately, this approach does not work when evaluating highly effective ranking systems, such as those emerging from the advances in machine learning. Recent work demonstrates that moving away from pointwise item and metric evaluation can be a more effective approach to the offline evaluation of systems. This tutorial, intended for both researchers and practitioners, reviews early work in preference-based evaluation and covers recent developments in detail.

2023-01-01

WSDM (published)

doi.org

Price Forecasting in the Ontario Electricity Market via TriConvGRU Hybrid Model: Univariate vs. Multivariate Frameworks

Behdad Ehsani

Pierre-Olivier Pineau

Laurent Charlin

2023-01-01

SSRN Electronic Journal (published)

doi.org

Privacy-Aware Compression for Federated Learning Through Numerical Mechanism Design

Chuan Guo

Kamalika Chaudhuri

Pierre Stock

Michael Rabbat

In private federated learning (FL), a server aggregates differentially private updates from a large number of clients in order to train a ma… (see more)chine learning model. The main challenge in this setting is balancing privacy with both classification accuracy of the learnt model as well as the number of bits communicated between the clients and server. Prior work has achieved a good trade-off by designing a privacy-aware compression mechanism, called the minimum variance unbiased (MVU) mechanism, that numerically solves an optimization problem to determine the parameters of the mechanism. This paper builds upon it by introducing a new interpolation procedure in the numerical design process that allows for a far more efficient privacy analysis. The result is the new Interpolated MVU mechanism that is more scalable, has a better privacy-utility trade-off, and provides SOTA results on communication-efficient private FL on a variety of datasets.

2023-01-01

ICML (published)

openreview.net

PromptMix: A Class Boundary Augmentation Method for Large Language Model Distillation

Gaurav Sahu

Olga Vechtomova

Dzmitry Bahdanau

Issam Hadj Laradji

Data augmentation is a widely used technique to address the problem of text classification when there is a limited amount of training data. … (see more)Recent work often tackles this problem using large language models (LLMs) like GPT3 that can generate new examples given already available ones. In this work, we propose a method to generate more helpful augmented data by utilizing the LLM's abilities to follow instructions and perform few-shot classifications. Our specific PromptMix method consists of two steps: 1) generate challenging text augmentations near class boundaries; however, generating borderline examples increases the risk of false positives in the dataset, so we 2) relabel the text augmentations using a prompting-based LLM classifier to enhance the correctness of labels in the generated data. We evaluate the proposed method in challenging 2-shot and zero-shot settings on four text classification datasets: Banking77, TREC6, Subjectivity (SUBJ), and Twitter Complaints. Our experiments show that generating and, crucially, relabeling borderline examples facilitates the transfer of knowledge of a massive LLM like GPT3.5-turbo into smaller and cheaper classifiers like DistilBERT

2023-01-01

EMNLP (published)

doi.org

openreview.net

Prototype-Sample Relation Distillation: Towards Replay-Free Continual Learning

Nader Asadi

MohammadReza Davari

Sudhir Mudur

Rahaf Aljundi

Eugene Belilovsky

In Continual learning (CL) balancing effective adaptation while combating catastrophic forgetting is a central challenge. Many of the recent… (see more) best-performing methods utilize various forms of prior task data, e.g. a replay buffer, to tackle the catastrophic forgetting problem. Having access to previous task data can be restrictive in many real-world scenarios, for example when task data is sensitive or proprietary. To overcome the necessity of using previous tasks' data, in this work, we start with strong representation learning methods that have been shown to be less prone to forgetting. We propose a holistic approach to jointly learn the representation and class prototypes while maintaining the relevance of old class prototypes and their embedded similarities. Specifically, samples are mapped to an embedding space where the representations are learned using a supervised contrastive loss. Class prototypes are evolved continually in the same latent space, enabling learning and prediction at any point. To continually adapt the prototypes without keeping any prior task data, we propose a novel distillation loss that constrains class prototypes to maintain relative similarities as compared to new task data. This method yields state-of-the-art performance in the task-incremental setting, outperforming methods relying on large amounts of data, and provides strong performance in the class-incremental setting without using any stored data points.

2023-01-01

ICML (published)

doi.org

openreview.net

Publisher Correction: Advancing ethics review practices in AI research

Madhulika Srikumar

Rebecca Finlay

Grace M. Abuhamad

Carolyn Ashurst

Rosie Campbell

Emily Campbell-Ratcliffe

Hudson Hongo