Skip to search formSkip to main contentSkip to account menu

Translating Embeddings for Modeling Multi-relational Data

TransE is proposed, a method which models relationships by interpreting them as translations operating on the low-dimensional embeddings of the entities, which proves to be powerful since extensive experiments show that TransE significantly outperforms state-of-the-art methods in link prediction on two knowledge bases.
View Paper (opens in a new tab)

End-to-End Object Detection with Transformers

This work presents a new method that views object detection as a direct set prediction problem, and demonstrates accuracy and run-time performance on par with the well-established and highly-optimized Faster RCNN baseline on the challenging COCO object detection dataset.
View PDF on arXiv (opens in a new tab)

Large-scale Simple Question Answering with Memory Networks

This paper studies the impact of multitask and transfer learning for simple question answering; a setting for which the reasoning required to answer is quite easy, as long as one can retrieve the correct evidence given a question, which can be difficult in large-scale conditions.
View PDF on arXiv (opens in a new tab)

WSABIE: Scaling Up to Large Vocabulary Image Annotation

This work proposes a strongly performing method that scales to image annotation datasets by simultaneously learning to optimize precision at the top of the ranked list of annotations for a given image and learning a low-dimensional joint embedding space for both images and annotations.
View via Publisher (opens in a new tab)

Parseval Networks: Improving Robustness to Adversarial Examples

It is shown that Parseval networks match the state-of-the-art in terms of accuracy on CIFAR-10/100 and Street View House Numbers while being more robust than their vanilla counterpart against adversarial examples.
View PDF on arXiv (opens in a new tab)

Fader Networks: Manipulating Images by Sliding Attributes

A new encoder-decoder architecture that is trained to reconstruct images by disentangling the salient information of the image and the values of attributes directly in the latent space is introduced, which results in much simpler training schemes and nicely scales to multiple attributes.
View PDF on arXiv (opens in a new tab)

Canonical Tensor Decomposition for Knowledge Base Completion

This work motivates and test a novel regularizer, based on tensor nuclear $p$-norms, and presents a reformulation of the problem that makes it invariant to arbitrary choices in the inclusion of predicates or their reciprocals in the dataset.
View PDF on arXiv (opens in a new tab)

Improving Neural Language Models with a Continuous Cache

A simplified version of memory augmented networks, which stores past hidden activations as memory and accesses them through a dot product with the current hidden activation, which is very efficient and scales to very large memory sizes.
View PDF on arXiv (opens in a new tab)

Music Source Separation in the Waveform Domain

Demucs is proposed, a new waveform-to-waveform model, which has an architecture closer to models for audio generation with more capacity on the decoder, and human evaluations show that Demucs has significantly higher quality than Conv-Tasnet, but slightly more contamination from other sources, which explains the difference in SDR.
View PDF on arXiv (opens in a new tab)

Tensor Decompositions for temporal knowledge base completion

A solution inspired by the canonical decomposition of tensors of order 4 is proposed for link prediction under temporal constraints and a new dataset for knowledge base completion constructed from Wikidata is proposed, larger than previous benchmarks by an order of magnitude, as a new reference for evaluating temporal and non-temporal link prediction methods.
View PDF on arXiv (opens in a new tab)
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)