Search Results for author:
Found 19 papers, 6 papers with code
Multi-Objective Recommendation via Multivariate Policy Learning
We frame this as a decision-making task, where the scalarisation weights are actions taken to maximise an overall North Star reward (e. g. long-term user retention or growth).
On Gradient Boosted Decision Trees and Neural Rankers: A Case-Study on Short-Video Recommendations at ShareChat
We highlight (1) neural networks' ability to handle large training data size, user- and item-embeddings allows for more accurate models than GBDTs in this setting, and (2) because GBDTs are less reliant on specialised hardware, they can provide an equally accurate model at a lower cost.
Should I send this notification? Optimizing push notifications decision making by modeling the future
In this work we focus on mobile push notifications, where the long term effects of recommender system decisions can be particularly strong.
Learning to Rank For Push Notifications Using Pairwise Expected Regret
Listwise ranking losses have been widely studied in recommender systems.
Deep Bayesian Bandits: Exploring in Online Personalized Recommendations
Recommender systems trained in a continuous learning fashion are plagued by the feedback loop problem, also known as algorithmic bias.
Model Size Reduction Using Frequency Based Double Hashing for Recommender Systems
The large model size usually entails a cost, in the range of millions of dollars, for storage and communication with the inference services.
Privacy-Aware Recommender Systems Challenge on Twitter's Home Timeline
Recommender systems constitute the core engine of most social network platforms nowadays, aiming to maximize user satisfaction along with other key business objectives.
Addressing Delayed Feedback for Continuous Training with Neural Networks in CTR prediction
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.
Smile, Be Happy :) Emoji Embedding for Visual Sentiment Analysis
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.
Frame Interpolation with Multi-Scale Deep Loss Functions and Generative Adversarial Networks
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.
Checkerboard artifact free sub-pixel convolution: A note on sub-pixel convolution, resize convolution and convolution resize
Compared to sub-pixel convolution initialized with schemes designed for standard convolution kernels, it is free from checkerboard artifacts immediately after initialization.
Lossy Image Compression with Compressive Autoencoders
We propose a new approach to the problem of optimizing autoencoders for lossy image compression.
Fast Face-swap Using Convolutional Neural Networks
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.
Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensation
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)
Amortised MAP Inference for Image Super-resolution
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.
Is the deconvolution layer the same as a convolutional layer?
In this note, we want to focus on aspects related to two questions most people asked us at CVPR about the network we presented.
Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network
This means that the super-resolution (SR) operation is performed in HR space.
Ranked #1 on
Video Super-Resolution
on Xiph HD - 4x upscaling
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
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
Patch-based Evaluation of Image Segmentation
The ideal similarity measure should be unbiased to segmentations of different volume and complexity, and be able to quantify and visualise segmentation bias.
