Search Results for author:
Found 23 papers, 10 papers with code
Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Report
While numerous solutions have been proposed for this problem in the past, they are usually not compatible with low-power mobile NPUs having many computational and memory constraints.
Learning Knowledge Representation with Meta Knowledge Distillation for Single Image Super-Resolution
In addition, the KRNets are optimized in a meta-learning manner to ensure the knowledge transferring and the student learning are beneficial to improving the reconstructed quality of the student.
Adaptive Domain Interest Network for Multi-domain Recommendation
Industrial recommender systems usually hold data from multiple business scenarios and are expected to provide recommendation services for these scenarios simultaneously.
Boosting Cross-Domain Speech Recognition with Self-Supervision
The cross-domain performance of automatic speech recognition (ASR) could be severely hampered due to the mismatch between training and testing distributions.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Decoupled Federated Learning for ASR with Non-IID Data
Secondly, to reduce the communication and computation costs, we propose decoupled federated learning (DecoupleFL).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
WSLRec: Weakly Supervised Learning for Neural Sequential Recommendation Models
Motivated by the observation that model-free methods like behavioral retargeting (BR) and item-based collaborative filtering (ItemCF) hit different parts of the user-item relevance compared to neural sequential recommendation models, we propose a novel model-agnostic training approach called WSLRec, which adopts a three-stage framework: pre-training, top-$k$ mining, and fine-tuning.
Approximate Nearest Neighbor Search under Neural Similarity Metric for Large-Scale Recommendation
In this paper, we propose a novel method to extend ANN search to arbitrary matching functions, e. g., a deep neural network.
MBCT: Tree-Based Feature-Aware Binning for Individual Uncertainty Calibration
In previous work, researchers have developed several calibration methods to post-process the outputs of a predictor to obtain calibrated values, such as binning and scaling methods.
Optical Flow Reusing for High-Efficiency Space-Time Video Super Resolution
In this paper, we consider the task of space-time video super-resolution (ST-VSR), which can increase the spatial resolution and frame rate for a given video simultaneously.
Optical Flow Estimation
Space-time Video Super-resolution
+2
Wav2vec-S: Semi-Supervised Pre-Training for Low-Resource ASR
In this work, in order to build a better pre-trained model for low-resource ASR, we propose a pre-training approach called wav2vec-S, where we use task-specific semi-supervised pre-training to refine the self-supervised pre-trained model for the ASR task thus more effectively utilize the capacity of the pre-trained model to generate task-specific representations for ASR.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Context-aware Tree-based Deep Model for Recommender Systems
Vertically, a parent fusion layer is designed in M to transmit the user preference representation in higher levels of T to the current level, grasping the essence that tree-based methods are generating the candidate set from coarse to detail during the beam search retrieval.
Exploiting Adapters for Cross-lingual Low-resource Speech Recognition
Based on our previous MetaAdapter that implicitly leverages adapters, we propose a novel algorithms called SimAdapter for explicitly learning knowledge from adapters.
Ranked #1 on
Cross-Lingual ASR
on Common Voice
Truncation-Free Matching System for Display Advertising at Alibaba
When receiving a user request, matching system (i) finds the crowds that the user belongs to; (ii) retrieves all ads that have targeted those crowds.
Multi-Accent Adaptation based on Gate Mechanism
To jointly train the acoustic model and the accent classifier, we propose the multi-task learning with gate mechanism (MTL-G).
Domain Adaptation Using Class Similarity for Robust Speech Recognition
Then, for each class, probabilities of this class are used to compute a mean vector, which we refer to as mean soft labels.
Learning Optimal Tree Models Under Beam Search
Retrieving relevant targets from an extremely large target set under computational limits is a common challenge for information retrieval and recommendation systems.
A Survey of Optimization Methods from a Machine Learning Perspective
Machine learning develops rapidly, which has made many theoretical breakthroughs and is widely applied in various fields.
Joint Optimization of Tree-based Index and Deep Model for Recommender Systems
The previous work Tree-based Deep Model (TDM) \cite{zhu2018learning} greatly improves recommendation accuracy using tree index.
Learning Tree-based Deep Model for Recommender Systems
In systems with large corpus, however, the calculation cost for the learnt model to predict all user-item preferences is tremendous, which makes full corpus retrieval extremely difficult.
Deep Interest Network for Click-Through Rate Prediction
In this way, user features are compressed into a fixed-length representation vector, in regardless of what candidate ads are.
Ranked #1 on
Click-Through Rate Prediction
on Amazon
Optimized Cost per Click in Taobao Display Advertising
Moreover, the platform has to be responsible for the business revenue and user experience.
Deep Transfer Learning with Joint Adaptation Networks
Deep networks have been successfully applied to learn transferable features for adapting models from a source domain to a different target domain.
Ranked #2 on
Domain Adaptation
on HMDBfull-to-UCF
Multi-Source Unsupervised Domain Adaptation
Transfer Learning
Unsupervised Domain Adaptation with Residual Transfer Networks
In this paper, we propose a new approach to domain adaptation in deep networks that can jointly learn adaptive classifiers and transferable features from labeled data in the source domain and unlabeled data in the target domain.
