Publications

Commonality in Recommender Systems: Evaluating Recommender Systems to Enhance Cultural Citizenship
Andres Ferraro
Gustavo Ferreira
Fernando Diaz
Georgina Born
2023-02-21
ArXiv (prépublication)
doi.org
arxiv.org
Steerable Equivariant Representation Learning
Sangnie Bhardwaj
Willie McClinton
Tongzhou Wang
Guillaume Lajoie
Chen Sun
Phillip Isola
Dilip Krishnan
Pre-trained deep image representations are useful for post-training tasks such as classification through transfer learning, image retrieval,… (voir plus) and object detection. Data augmentations are a crucial aspect of pre-training robust representations in both supervised and self-supervised settings. Data augmentations explicitly or implicitly promote invariance in the embedding space to the input image transformations. This invariance reduces generalization to those downstream tasks which rely on sensitivity to these particular data augmentations. In this paper, we propose a method of learning representations that are instead equivariant to data augmentations. We achieve this equivariance through the use of steerable representations. Our representations can be manipulated directly in embedding space via learned linear maps. We demonstrate that our resulting steerable and equivariant representations lead to better performance on transfer learning and robustness: e.g. we improve linear probe top-1 accuracy by between 1% to 3% for transfer; and ImageNet-C accuracy by upto 3.4%. We further show that the steerability of our representations provides significant speedup (nearly 50x) for test-time augmentations; by applying a large number of augmentations for out-of-distribution detection, we significantly improve OOD AUC on the ImageNet-C dataset over an invariant representation.
2023-02-21
ArXiv (prépublication)
doi.org
openreview.net
Interpret Your Care: Predicting the Evolution of Symptoms for Cancer Patients
Rupali Bhati
Jennifer Jones
Audrey Durand
Cancer treatment is an arduous process for patients and causes many side-effects during and post-treatment. The treatment can affect almost … (voir plus)all body systems and result in pain, fatigue, sleep disturbances, cognitive impairments, etc. These conditions are often under-diagnosed or under-treated. In this paper, we use patient data to predict the evolution of their symptoms such that treatment-related impairments can be prevented or effects meaningfully ameliorated. The focus of this study is on predicting the pain and tiredness level of a patient post their diagnosis. We implement an interpretable decision tree based model called LightGBM on real-world patient data consisting of 20163 patients. There exists a class imbalance problem in the dataset which we resolve using the oversampling technique of SMOTE. Our empirical results show that the value of the previous level of a symptom is a key indicator for prediction and the weighted average deviation in prediction of pain level is 3.52 and of tiredness level is 2.27.
2023-02-18
ArXiv (prépublication)
doi.org
arxiv.org
LAGrad: Statically Optimized Differentiable Programming in MLIR
Mai Jacob Peng
Christophe Dubach
2023-02-16
International Conference on Compiler Construction (publié)
doi.org
Spatio-temporal hard attention learning for skeleton-based activity recognition
Bahareh Nikpour
Narges Armanfard
2023-02-16
Pattern Recognition (inconnu)
doi.org
Effects of incoming particle energy and cluster size on the G-value of hydrated electrons.
Alaina Bui
H. Bekerat
Lilian Childress
Jack C Sankey
Jan Seuntjens
S. Enger
2023-02-15
Physica medica (Testo stampato) (publié)
doi.org
MOT: A Multi-Omics Transformer for Multiclass Classification Tumour Types Predictions
Mazid Osseni
Prudencio Tossou
Franccois Laviolette
J. Corbeil
2023-02-15
Proceedings of the 16th International Joint Conference on Biomedical Engineering Systems and Technologies (publié)
doi.org
Refactoring practices in the context of data-intensive systems
Biruk Asmare Muse
Foutse Khomh
Giuliano Antoniol
2023-02-15
Empirical Software Engineering (publié)
doi.org
Learning to Substitute Ingredients in Recipes
Bahare Fatemi
Quentin Duval
Rohit Girdhar
Michal Drozdzal
Adriana Romero
Recipe personalization through ingredient substitution has the potential to help people meet their dietary needs and preferences, avoid pote… (voir plus)ntial allergens, and ease culinary exploration in everyone's kitchen. To address ingredient substitution, we build a benchmark, composed of a dataset of substitution pairs with standardized splits, evaluation metrics, and baselines. We further introduce Graph-based Ingredient Substitution Module (GISMo), a novel model that leverages the context of a recipe as well as generic ingredient relational information encoded within a graph to rank plausible substitutions. We show through comprehensive experimental validation that GISMo surpasses the best performing baseline by a large margin in terms of mean reciprocal rank. Finally, we highlight the benefits of GISMo by integrating it in an improved image-to-recipe generation pipeline, enabling recipe personalization through user intervention. Quantitative and qualitative results show the efficacy of our proposed system, paving the road towards truly personalized cooking and tasting experiences.
2023-02-14
ArXiv (prépublication)
doi.org
arxiv.org
New wave theory
Paul François
2023-02-14
Development (publié)
doi.org
Score-based Diffusion Models in Function Space
Jae Hyun Lim
Nikola B. Kovachki
R. Baptista
Christopher Beckham
Kamyar Azizzadenesheli
Jean Kossaifi
Vikram Voleti
Jiaming Song
Karsten Kreis
Jan Kautz
Christopher Pal
Arash Vahdat
Animashree Anandkumar
2023-02-13
ArXiv (prépublication)
doi.org
arxiv.org
The Stable Entropy Hypothesis and Entropy-Aware Decoding: An Analysis and Algorithm for Robust Natural Language Generation
Kushal Arora
Timothy J. O'Donnell
Doina Precup
Jason Aaron Edward Weston
Jackie C.K.Cheung
State-of-the-art language generation models can degenerate when applied to open-ended generation problems such as text completion, story gen… (voir plus)eration, or dialog modeling. This degeneration usually shows up in the form of incoherence, lack of vocabulary diversity, and self-repetition or copying from the context. In this paper, we postulate that ``human-like'' generations usually lie in a narrow and nearly flat entropy band, and violation of these entropy bounds correlates with degenerate behavior. Our experiments show that this stable narrow entropy zone exists across models, tasks, and domains and confirm the hypothesis that violations of this zone correlate with degeneration. We then use this insight to propose an entropy-aware decoding algorithm that respects these entropy bounds resulting in less degenerate, more contextual, and"human-like"language generation in open-ended text generation settings.
2023-02-13
ArXiv (prépublication)
doi.org
arxiv.org