In this work we focus on mobile push notifications, where the long term effects of recommender system decisions can be particularly strong.
Listwise ranking losses have been widely studied in recommender systems.
Recommender systems trained in a continuous learning fashion are plagued by the feedback loop problem, also known as algorithmic bias.
no code implementations • 28 Jul 2020 • Caojin Zhang, Yicun Liu, Yuanpu Xie, Sofia Ira Ktena, Alykhan Tejani, Akshay Gupta, Pranay Kumar Myana, Deepak Dilipkumar, Suvadip Paul, Ikuhiro Ihara, Prasang Upadhyaya, Ferenc Huszar, Wenzhe Shi
The large model size usually entails a cost, in the range of millions of dollars, for storage and communication with the inference services.
no code implementations • 28 Apr 2020 • Luca Belli, Sofia Ira Ktena, Alykhan Tejani, Alexandre Lung-Yut-Fon, Frank Portman, Xiao Zhu, Yuanpu Xie, Akshay Gupta, Michael Bronstein, Amra Delić, Gabriele Sottocornola, Walter Anelli, Nazareno Andrade, Jessie Smith, Wenzhe Shi
Recommender systems constitute the core engine of most social network platforms nowadays, aiming to maximize user satisfaction along with other key business objectives.
The focus of this paper is to identify the best combination of loss functions and models that enable large-scale learning from a continuous stream of data in the presence of delayed labels.
Additionally, we introduce a novel emoji representation based on their visual emotional response which supports a deeper understanding of the emoji modality and their usage on social media.
To improve the quality of synthesised intermediate video frames, our network is jointly supervised at different levels with a perceptual loss function that consists of an adversarial and two content losses.
Compared to sub-pixel convolution initialized with schemes designed for standard convolution kernels, it is free from checkerboard artifacts immediately after initialization.
We consider the problem of face swapping in images, where an input identity is transformed into a target identity while preserving pose, facial expression, and lighting.
Convolutional neural networks have enabled accurate image super-resolution in real-time.
Ranked #11 on Video Super-Resolution on MSU Video Upscalers: Quality Enhancement (VMAF metric)
We show that, using this architecture, the amortised MAP inference problem reduces to minimising the cross-entropy between two distributions, similar to training generative models.
In this note, we want to focus on aspects related to two questions most people asked us at CVPR about the network we presented.
This means that the super-resolution (SR) operation is performed in HR space.
Ranked #1 on Video Super-Resolution on Xiph HD - 4x upscaling
The adversarial loss pushes our solution to the natural image manifold using a discriminator network that is trained to differentiate between the super-resolved images and original photo-realistic images.
Ranked #3 on Image Super-Resolution on VggFace2 - 8x upscaling
The ideal similarity measure should be unbiased to segmentations of different volume and complexity, and be able to quantify and visualise segmentation bias.