Tufts Machine Learning

graph-generation-EDGE

EDGE: Efficient and Degree-Guided Graph Generation via Discrete Diffusion Modeling

KCN

Kriging Convolutional Networks (KCN) in Tensoflow

kcn-torch

SSL-vs-SSL-benchmark

Code for benchmark comparing self-supervised and semi-supervised deep classifiers for medical images

categorical-from-binary

Code for the paper "Easy Variational Inference for Categorical Models via an Independent Binary Approximation"

cumulative-link-models

Code for cumulative link models for ordinal regression that support differentiable learning ala PyTorch

Graph-Generation-MLE

SepNorm

G2PT

Graph generative pre-trained transformer

SupContrast

PyTorch implementation of "SINCERE: Supervised Information Noise-Contrastive Estimation REvisited"

InterLUDE

Code for ICML 2024 paper "InterLUDE: Interactions between Labeled and Unlabeled Data to Enhance Semi-supervised Learning"

pchmm-missing-data-limited-labels

Repository for paper "Prediction-Constrained Markov Models for Medical Time Series with Missing Data and Few Labels" at NeurIPS workshop (Learning from Time Series For Health)

SAMIL

Code for the paper Detecting Heart Disease from Multi-View Ultrasound Images via Supervised Attention Multiple Instance Learning

team-dynamics-time-series

Models for capturing multi-level dynamics of individuals on a team acting in coordinated way over time

data-driven-missingness-cru-irregular-timeseries

Code for irregular time-series models with missing-not-at-random assumption

data-emphasized-ELBo

Code for FITML 2024 workshop paper on data-emphasized evidence lower bound for learning regularization parameters

extrapolating-classifier-accuracy-to-larger-datasets

GRAPE-MUST

This repository holds the code and models for the paper Graph Pruning for Enumeration of Minimal Unsatisfiable Subsets, published at AISTATS2024

hugheslab-onboarding

Onboarding info for hugheslab (HPC cluster, etc.)

bdl-transfer-learning

dsarf_agentformer_baseline_for_hsrdm

Baselines on Figure 8 and Basketball data for paper titled 'Discovering group dynamics in synchronous time series via hierarchical recurrent switching-state models'

DAGG-Rout-VI

decision-aware-topk

differentiable-top-k

Code for differentiable learning of functions that involve selecting the top K of many elements

moco-v3

PyTorch implementation of MoCo v3 https//arxiv.org/abs/2104.02057

opioid-overdose-models

Given previous times and locations of opioid overdose deaths, can we predict where future interventions would be effective?

RobustSSLBenchmark

A benchmark for robust semi-supervised learning in open environments.

SincereClustering

SupervisionInterpolation

SupportBroadening