Publications

Margarida Carvalho

2023-05-23

Integration of Constraint Programming, Artificial Intelligence, and Operations Research (published)

Should We Attend More or Less? Modulating Attention for Fairness

A. Zayed

Goncalo Mordido

Samira Shabanian

Sarath Chandar

2023-05-22

ArXiv (preprint)

Data Imputation with an Autoencoder and MAGIC

Devin Eddington

Andres Felipe Duque Correa

Kevin R. Moon

Missing data is a common problem in many applications. Imputing missing values is a challenging task, as the imputations need to be accurate… (see more) and robust to avoid introducing bias in downstream analysis. In this paper, we propose an ensemble method that combines the strengths of a manifold learning-based imputation method called MAGIC and an autoencoder deep learning model. We call our method Deep MAGIC. Deep MAGIC is trained on a linear combination of the mean squared error of the original data and the mean squared error of the MAGIC-imputed data. Experimental results on three benchmark datasets show that Deep MAGIC outperforms several state-of-the-art imputation methods, demonstrating its effectiveness and robustness in handling large amounts of missing data.

2023-05-21

SampTA/2023/Conference (published)

openreview.net

Graph Fourier MMD for Signals on Graphs

Samuel Leone

Aarthi Venkat

Guillaume Huguet

Alexander Tong

Smita Krishnaswamy

While numerous methods have been proposed for computing distances between probability distributions in Euclidean space, relatively little at… (see more)tention has been given to computing such distances for distributions on graphs. However, there has been a marked increase in data that either lies on graph (such as protein interaction networks) or can be modeled as a graph (single cell data), particularly in the biomedical sciences. Thus, it becomes important to find ways to compare signals defined on such graphs. Here, we propose Graph Fourier MMD (GFMMD), a novel distance between distributions and signals on graphs. GFMMD is defined via an optimal witness function that is both smooth on the graph and maximizes the difference in expectation between the pair of distributions on the graph. We find an analytical solution to this optimization problem as well as an embedding of distributions that results from this method. We also prove several properties of this method including scale invariance and applicability to disconnected graphs. We showcase it on graph benchmark datasets as well on single cell RNA-sequencing data analysis. In the latter, we use the GFMMD-based gene embeddings to find meaningful gene clusters. We also propose a novel type of score for gene selection called gene localization score which helps select genes for cellular state space characterization.

2023-05-21

SampTA/2023/Conference (published)

openreview.net

Hybrid GRAND Sphere Decoding: Accelerated GRAND for Low-Rate Codes

Huayi Zhou

Warren Gross

Guessing random additive noise decoding (GRAND) and sphere decoding (SD) are two algorithms that can achieve maximum likelihood decoding. In… (see more) this paper, a hybrid GRAND-SD (HGRAND) scheme is proposed to extend GRAND to low-rate codes. An accelerated GRAND decoder, assisted by a sphere decoder running in parallel and giving hints to it to allow skipping of certain candidates allows HGRAND to achieve a latency below the minimum latency of the individual component decoders while guaranteeing error-correction performance.

2023-05-21

International Symposium on Circuits and Systems (published)

Manifold Alignment with Label Information

Andres F. Duque Correa

Myriam Lizotte

Kevin R. Moon

Multi-domain data is becoming increasingly common and presents both challenges and opportunities in the data science community. The integrat… (see more)ion of distinct data-views can be used for exploratory data analysis, and benefit downstream analysis including machine learning related tasks. With this in mind, we present a novel manifold alignment method called MALI (Manifold alignment with label information) that learns a correspondence between two distinct domains. MALI belongs to a middle ground between the more commonly addressed semi-supervised manifold alignment, where some known correspondences between the two domains are assumed to be known beforehand, and the purely unsupervised case, where no information linking both domains is available. To do this, MALI learns the manifold structure in both domains via a diffusion process and then leverages discrete class labels to guide the alignment. MALI recovers a pairing and a common representation that reveals related samples in both domains. We show that MALI outperforms the current state-of-the-art manifold alignment methods across multiple datasets.

2023-05-21

SampTA/2023/Conference (published)

openreview.net

ToxBuster: In-game Chat Toxicity Buster with BERT

Zachary Yang

Yasmine Maricar

M. Davari

Nicolas Grenon-Godbout

Reihaneh Rabbany

Detecting toxicity in online spaces is challenging and an ever more pressing problem given the increase in social media and gaming consumpti… (see more)on. We introduce ToxBuster, a simple and scalable model trained on a relatively large dataset of 194k lines of game chat from Rainbow Six Siege and For Honor, carefully annotated for different kinds of toxicity. Compared to the existing state-of-the-art, ToxBuster achieves 82.95% (+7) in precision and 83.56% (+57) in recall. This improvement is obtained by leveraging past chat history and metadata. We also study the implication towards real-time and post-game moderation as well as the model transferability from one game to another.

2023-05-21

ArXiv (preprint)

Training Acceleration of Frequency Domain CNNs Using Activation Compression

Seyyed Hasan Mozafari

James J. Clark

Warren Gross

Brett Meyer

Reducing the complexity of training convolutional neural networks results in lower energy consumption expended during training, or higher ac… (see more)curacy by admitting a greater number of training epochs within a training time budget. During backpropagation, a considerable amount of temporary data is offloaded from GPU memory to CPU memory, increasing training time. In this paper, we address this training time overhead by introducing an activation compression technique for frequency domain convolutional neural networks. Applying this compression technique on frequency domain AlexNet results in activation compression of 57.7%, and a reduction of training time by 23%, with a negligible effect on classification accuracy.

2023-05-21

International Symposium on Circuits and Systems (published)

Idiolect: A Reconfigurable Voice Coding Assistant

Breandan Considine

Nicholas Albion

Xujie Si

This paper presents Idiolect, an open source 1 IDE plugin for voice coding and a novel approach to building bots that allows for users to de… (see more)fine custom commands on-the-fly. Unlike traditional chatbots, Idiolect does not pretend to be an omniscient virtual assistant but rather a reconfigurable voice programming system that empowers users to create their own commands and actions dynamically, without rebuilding or restarting the application. We offer an experience report describing the tool itself, illustrate some example use cases, and reflect on several lessons learned during the tool’s development.

2023-05-20

2023 IEEE/ACM 5th International Workshop on Bots in Software Engineering (BotSE) (published)

Neural Bee Colony Optimization: A Case Study in Public Transit Network Design

Andrew Holliday

Gregory Dudek

In this work we explore the combination of metaheuristics and learned neural network solvers for combinatorial optimization. We do this in t… (see more)he context of the transit network design problem, a uniquely challenging combinatorial optimization problem with real-world importance. We train a neural network policy to perform single-shot planning of individual transit routes, and then incorporate it as one of several sub-heuristics in a modified Bee Colony Optimization (BCO) metaheuristic algorithm. Our experimental results demonstrate that this hybrid algorithm outperforms the learned policy alone by up to 20% and the original BCO algorithm by up to 53% on realistic problem instances. We perform a set of ablations to study the impact of each component of the modified algorithm.

2023-05-18

ArXiv (preprint)

NollySenti: Leveraging Transfer Learning and Machine Translation for Nigerian Movie Sentiment Classification

Iyanuoluwa Shode

David Ifeoluwa Adelani

Jing Peng

Anna Feldman

Africa has over 2000 indigenous languages but they are under-represented in NLP research due to lack of datasets. In recent years, there hav… (see more)e been progress in developing labelled corpora for African languages. However, they are often available in a single domain and may not generalize to other domains. In this paper, we focus on the task of sentiment classification for cross-domain adaptation. We create a new dataset, Nollywood movie reviews for five languages widely spoken in Nigeria (English, Hausa, Igbo, Nigerian Pidgin, and Yoruba). We provide an extensive empirical evaluation using classical machine learning methods and pre-trained language models. By leveraging transfer learning, we compare the performance of cross-domain adaptation from Twitter domain, and cross-lingual adaptation from English language. Our evaluation shows that transfer from English in the same target domain leads to more than 5% improvement in accuracy compared to transfer from Twitter in the same language. To further mitigate the domain difference, we leverage machine translation from English to other Nigerian languages, which leads to a further improvement of 7% over cross-lingual evaluation. While machine translation to low-resource languages are often of low quality, our analysis shows that sentiment related words are often preserved.

2023-05-18

ArXiv (preprint)

The potential for co-operatives to mitigate AI ethics catastrophes: perspectives from media analysis

David Marino

AJung Moon

Would the world have seen less AI-related scandals if more AI companies operated as co-operatives? As a response to multiple high profile te… (see more)ch scandals within the last decade, there has been an increased call for introducing more accountability in the AI industry. However, it is unclear to what degree the proposed efforts have been or will be effective in practice. The question remains whether these incremental, multi-stakeholder AI ethics efforts are in fact trying to address a fundamentally systemic issue inherent to the existing corporate power structure. As an attempt to address this question, we gain an understanding of the major themes in high profile AI-related catastrophes in the last four years (2018–2021) through an inductive media analysis. We then investigate how the principle of democratic gov-ernance and distributive executive power - core to co-operative organization structure - could have prevented or mitigated the contributing factors of the reported events. We find that the vast majority (71%) of the recent AI ethics scandals are not the result of a lack of knowledge or tools, but attributed to power dynamics that hinder the ability of internal stakeholders from taking action. We present the co-operative governance structure as a possible mitigating solution to addressing future AI ethics catastrophes, and provide a critical look at practical challenges inherent to AI co-operatives.

2023-05-18

Ethics: An International Journal of Social, Political, and Legal Philosophy (published)