55 citations · 143 across the 14 of their papers we have counts for
15 papers
What Constitutes Good Contrastive Learning in Time-Series Forecasting?
Chiyu Zhang, Qi Yan, Lili Meng +1
In recent years, the introduction of self-supervised contrastive learning (SSCL) has demonstrated remarkable improvements in representation learning across various domains, includi…
Robust Reinforcement Learning Objectives for Sequential Recommender Systems
Melissa Mozifian, Tristan Sylvain, Dave Evans +1
Attention-based sequential recommendation methods have shown promise in accurately capturing users' evolving interests from their past interactions. Recent research has also explor…
Self-supervised multimodal neuroimaging yields predictive representations for a spectrum of Alzheimer's phenotypes
Alex Fedorov, Eloy Geenjaar, Lei Wu +7
Recent neuroimaging studies that focus on predicting brain disorders via modern machine learning approaches commonly include a single modality and rely on supervised over-parameter…
Scaleformer: Iterative Multi-scale Refining Transformers for Time Series Forecasting
Amin Shabani, Amir Abdi, Lili Meng +1
The performance of time series forecasting has recently been greatly improved by the introduction of transformers. In this paper, we propose a general multi-scale framework that ca…
Self-Supervised Multimodal Domino: in Search of Biomarkers for Alzheimer's Disease
Alex Fedorov, Tristan Sylvain, Eloy Geenjaar +7
Sensory input from multiple sources is crucial for robust and coherent human perception. Different sources contribute complementary explanatory factors. Similarly, research studies…
On self-supervised multi-modal representation learning: An application to Alzheimer's disease
Alex Fedorov, Lei Wu, Tristan Sylvain +5
Introspection of deep supervised predictive models trained on functional and structural brain imaging may uncover novel markers of Alzheimer's disease (AD). However, supervised tra…
Zero-Shot Learning from scratch (ZFS): leveraging local compositional representations
Tristan Sylvain, Linda Petrini, R Devon Hjelm
Zero-shot classification is a generalization task where no instance from the target classes is seen during training. To allow for test-time transfer, each class is annotated with s…
Cross-Modal Information Maximization for Medical Imaging: CMIM
Tristan Sylvain, Francis Dutil, Tess Berthier +4
In hospitals, data are siloed to specific information systems that make the same information available under different modalities such as the different medical imaging exams the pa…
Image-to-image Mapping with Many Domains by Sparse Attribute Transfer
Matthew Amodio, Rim Assouel, Victor Schmidt +3
Unsupervised image-to-image translation consists of learning a pair of mappings between two domains without known pairwise correspondences between points. The current convention is…
Object-Centric Image Generation from Layouts
Tristan Sylvain, Pengchuan Zhang, Yoshua Bengio +2
Despite recent impressive results on single-object and single-domain image generation, the generation of complex scenes with multiple objects remains challenging. In this paper, we…
Locality and compositionality in zero-shot learning
Tristan Sylvain, Linda Petrini, Devon Hjelm
In this work we study locality and compositionality in the context of learning representations for Zero Shot Learning (ZSL). In order to well-isolate the importance of these proper…
Joint Learning of Generative Translator and Classifier for Visually Similar Classes
ByungIn Yoo, Tristan Sylvain, Yoshua Bengio +1
In this paper, we propose a Generative Translation Classification Network (GTCN) for improving visual classification accuracy in settings where classes are visually similar and dat…
Learning to rank for censored survival data
Margaux Luck, Tristan Sylvain, Joseph Paul Cohen +3
Survival analysis is a type of semi-supervised ranking task where the target output (the survival time) is often right-censored. Utilizing this information is a challenge because i…
Deep Learning for Patient-Specific Kidney Graft Survival Analysis
Margaux Luck, Tristan Sylvain, Héloïse Cardinal +2
An accurate model of patient-specific kidney graft survival distributions can help to improve shared-decision making in the treatment and care of patients. In this paper, we propos…
Diet Networks: Thin Parameters for Fat Genomics
Adriana Romero, Pierre Luc Carrier, Akram Erraqabi +7
Learning tasks such as those involving genomic data often poses a serious challenge: the number of input features can be orders of magnitude larger than the number of training exam…