Analyzing domain shift when using additional data for the MICCAI KiTS23 Challenge

no code implementations • 5 Sep 2023 • George Stoica, Mihaela Breaban, Vlad Barbu

Using additional training data is known to improve the results, especially for medical image 3D segmentation where there is a lack of training material and the model needs to generalize well from few available data.

ZipIt! Merging Models from Different Tasks without Training

1 code implementation • 4 May 2023 • George Stoica, Daniel Bolya, Jakob Bjorner, Pratik Ramesh, Taylor Hearn, Judy Hoffman

While this works for models trained on the same task, we find that this fails to account for the differences in models trained on disjoint tasks.

Dynamic Batch Adaptation

no code implementations • 1 Aug 2022 • Cristian Simionescu, George Stoica, Robert Herscovici

Additionally, we find that DBA produces an increased improvement over standard optimizers when used in data scarce conditions where, in addition to convergence speed, it also significantly improves model generalization, managing to train a network with a single fully connected hidden layer using only 1% of the MNIST dataset to reach 97. 79% test accuracy.

Re-TACRED: Addressing Shortcomings of the TACRED Dataset

1 code implementation • 16 Apr 2021 • George Stoica, Emmanouil Antonios Platanios, Barnabás Póczos

Finally, aside from our analysis we also release Re-TACRED, a new completely re-annotated version of the TACRED dataset that can be used to perform reliable evaluation of relation extraction models.

Relation Extraction Sentence

Improving Relation Extraction by Leveraging Knowledge Graph Link Prediction

1 code implementation • 9 Dec 2020 • George Stoica, Emmanouil Antonios Platanios, Barnabás Póczos

Relation extraction (RE) aims to predict a relation between a subject and an object in a sentence, while knowledge graph link prediction (KGLP) aims to predict a set of objects, O, given a subject and a relation from a knowledge graph.

Link Prediction Multi-Task Learning +4

Contextual Parameter Generation for Knowledge Graph Link Prediction

1 code implementation • 3 Apr 2020 • George Stoica, * Otilia Stretcu, * Emmanouil Antonios Platanios, * Tom M. Mitchell, Barnabás Póczos

More specifically, we treat relations as the context in which source entities are processed to produce predictions, by using relation embeddings to generate the parameters of a model operating over source entity embeddings.

Entity Embeddings Link Prediction +1