Amazon Electronic Products Network Analysis

GCN transductive cross validation.

Graph Convolutional Networks, Graph Attention Networks, Gated Graph Neural Net, Mixhop

Pytorch implementation of Meta-Learned Confidence for Few-shot Learning

Object detection using SSL techniques. This is a semester project done in Summer 2021 as part of our coursework under the Faculty of Computer Science department at Otto-von-Guericke University, Magdeburg Germany.

Exploring evaluating the adversarial robustness of transductive-learning based defenses.

(NeurIPS 2021) Realistic Evaluation of Transductive Few-Shot Learning

A GridSearchCV-like hyperparameter optimizer for clustering (no cross-validation).

(CVPR 2021) Code for our method RePRI for Few-Shot Segmentation. Paper at http://arxiv.org/abs/2012.06166

Official repository for the paper TRIDENT: Transductive Decoupled Variational Inference for Few Shot Classification

(NeurIPS 2020) Transductive Information Maximization for Few-Shot Learning https://arxiv.org/abs/2008.11297

Segmentação Semi-Supervisionada de Imagens através de Dinâmicas Coletivas em Redes Complexas

Code for "Training-free Graph Neural Networks and the Power of Labels as Features" (TMLR 2024)

30 Semi-Supervised Learning Algorithms

Graph Attention Networks (GATs) for node classification and regression tasks

Open-source code for the paper "Enhancing Remote Sensing Vision-Language Models for Zero-Shot Scene Classification"