今日论文|谷歌：差分私有机器学习&谷歌：用模拟用户测量推荐系统性能&队列学习&MORE

Posted 2021-04-27 AI日读

1月13日人工智能领域新增论文 171篇，AI日读精选其中 37篇推荐给大家。这些论文主要来自AAAI，ICIP，ICPR，VLDB等会议与期刊。其中包含 计算机视觉论文11篇[1-11]， 自然语言处理论文6篇[12-17]， 方法论论文10篇[19-28]， 强化学习论文1篇[34]， 推荐系统论文2篇[35-36]。另外，本期还包含1个新构造的 数据集[18]，4篇 综述[29-32]，1个 开放平台或 工具包[33]，以及其他技术文章。点击文末 阅读原文即可下载。

标题文章序号：[26] & [36] & [34]

计算机视觉

Computer Vision

[1]

Quantum Cognitively Motivated Decision Fusion for Video Sentiment Analysis

Dimitris Gkoumas, Qiuchi Li, Shahram Dehdashti, Massimo Melucci, Yijun Yu, Dawei Song

摘 要：

原 文：http://arxiv.org/pdf/2101.04406v1

---

[2]

Superpixel-based Refinement for Object Proposal Generation

Christian Wilms, Simone Frintrop

摘 要：

原 文：http://arxiv.org/pdf/2101.04574v1

---

[3]

PvDeConv: Point-Voxel Deconvolution for Autoencoding CAD Construction in 3D

Kseniya Cherenkova, Djamila Aouada, Gleb Gusev

摘 要：

原 文：http://arxiv.org/pdf/2101.04493v1

---

[4]

TrackMPNN: A Message Passing Graph Neural Architecture for Multi-Object Tracking

Akshay Rangesh, Pranav Maheshwari, Mez Gebre, Siddhesh Mhatre, Vahid Ramezani, Mohan M. Trivedi

摘 要：

原 文：http://arxiv.org/pdf/2101.04206v1

---

[5]

Automated 3D solid reconstruction from 2D CAD using OpenCV

Ajay Bangalore Harish, Abhishek Rajendra Prasad

摘 要：

原 文：http://arxiv.org/pdf/2101.04248v1

---

[6]

3D-ANAS: 3D Asymmetric Neural Architecture Search for Fast Hyperspectral Image Classification

Haokui Zhang, Chengrong Gong, Yunpeng Bai, Zongwen Bai, Ying Li

摘 要：

原 文：http://arxiv.org/pdf/2101.04287v1

---

[7]

Random Transformation of Image Brightness for Adversarial Attack

Bo Yang, Kaiyong Xu, Hengjun Wang, Hengwei Zhang

摘 要：

原 文：http://arxiv.org/pdf/2101.04321v1

---

[8]

Take More Positives: A Contrastive Learning Framework for Unsupervised Person Re-Identification

Xuanyu He, Wei Zhang, Ran Song, Xiangyuan Lan

摘 要：

原 文：http://arxiv.org/pdf/2101.04340v1

---

[9]

UFA-FUSE: A novel deep supervised and hybrid model for multi-focus image fusion

Yongsheng Zang, Dongming Zhou, Changcheng Wang, Rencan Nie, Yanbu Guo

摘 要：

原 文：http://arxiv.org/pdf/2101.04506v1

---

[10]

Fine-grained Semantic Constraint in Image Synthesis

Pengyang Li, Donghui Wang

摘 要：

原 文：http://arxiv.org/pdf/2101.04558v1

---

[11]

Context Matters: Self-Attention for Sign Language Recognition

Fares Ben Slimane, Mohamed Bouguessa

摘 要：

原 文：http://arxiv.org/pdf/2101.04632v1

---

自然语言处理

Natural Language Processing

[12]

A character representation enhanced on-device Intent Classification

Sudeep Deepak Shivnikar, Himanshu Arora, Harichandana B S S

摘 要：

原 文：http://arxiv.org/pdf/2101.04456v1

---

[13]

BERT-GT: Cross-sentence n-ary relation extraction with BERT and Graph Transformer

Po-Ting Lai, Zhiyong Lu

摘 要：

原 文：http://arxiv.org/pdf/2101.04158v1

---

[14]

Text analysis in financial disclosures

Sridhar Ravula

摘 要：

原 文：http://arxiv.org/pdf/2101.04480v1

---

[15]

Of Non-Linearity and Commutativity in BERT

Sumu Zhao, Damian Pascual, Gino Brunner, Roger Wattenhofer

摘 要：

原 文：http://arxiv.org/pdf/2101.04547v1

---

[16]

AI- and HPC-enabled Lead Generation for SARS-CoV-2: Models and Processes to Extract Druglike Molecules Contained in Natural Language Text

Zhi Hong, J. Gregory Pauloski, Logan Ward, Kyle Chard, Ben Blaiszik, Ian Foster

摘 要：

原 文：http://arxiv.org/pdf/2101.04617v1

---

[17]

Dimensions of Commonsense Knowledge

Filip Ilievski, Alessandro Oltramari, Kaixin Ma, Bin Zhang, Deborah L. McGuinness, Pedro Szekely

摘 要：

原 文：http://arxiv.org/pdf/2101.04640v1

---

数据集

Dataset

[18]

The Multimodal Driver Monitoring Database: A Naturalistic Corpus to Study Driver Attention

Sumit Jha, Mohamed F. Marzban, Tiancheng Hu, Mohamed H. Mahmoud, Naofal Al-Dhahir Carlos Busso

摘 要：

原 文：http://arxiv.org/pdf/2101.04639v1

---

方法论

Methodology

[19]

DBTagger: Multi-Task Learning for Keyword Mapping in NLIDBs Using Bi-Directional Recurrent Neural Networks

Arif Usta, Akifhan Karakayali, Özgür Ulusoy

摘 要：

原 文：http://arxiv.org/pdf/2101.04226v1

---

[20]

Solving Common-Payoff Games with Approximate Policy Iteration

Samuel Sokota, Edward Lockhart, Finbarr Timbers, Elnaz Davoodi, Ryan D'Orazio, Neil Burch, Martin Schmid, Michael Bowling, Marc Lanctot

摘 要：

原 文：http://arxiv.org/pdf/2101.04237v1

---

[21]

Learning Intuitive Physics with Multimodal Generative Models

Sahand Rezaei-Shoshtari, Francois Robert Hogan, Michael Jenkin, David Meger, Gregory Dudek

摘 要：

原 文：http://arxiv.org/pdf/2101.04454v1

---

[22]

From Tinkering to Engineering: Measurements in Tensorflow Playground

Henrik Hoeiness, Axel Harstad, Gerald Friedland

摘 要：

原 文：http://arxiv.org/pdf/2101.04141v1

---

[23]

On the Convergence of Deep Networks with Sample Quadratic Overparameterization

Asaf Noy, Yi Xu, Yonathan Aflalo, Rong Jin

摘 要：

原 文：http://arxiv.org/pdf/2101.04243v1

---

[24]

Estimating Galactic Distances From Images Using Self-supervised Representation Learning

Md Abul Hayat, Peter Harrington, George Stein, Zarija Lukić, Mustafa Mustafa

摘 要：

原 文：http://arxiv.org/pdf/2101.04293v1

---

[25]

Seed Stocking Via Multi-Task Learning

Yunhe Feng, Wenjun Zhou

摘 要：

原 文：http://arxiv.org/pdf/2101.04333v1

---

[26]

Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning

Milad Nasr, Shuang Song, Abhradeep Thakurta, Nicolas Papernot, Nicholas Carlini

摘 要：

原 文：http://arxiv.org/pdf/2101.04535v1

---

[27]

An Early-Stopping Mechanism for DSCF Decoding of Polar Codes

Ilshat Sagitov, Pascal Giard

摘 要：

原 文：http://arxiv.org/pdf/2101.04586v1

---

[28]

Double-Adversarial Activation Anomaly Detection: Adversarial Autoencoders are Anomaly Generators

J.-P. Schulze, P. Sperl, K. Böttinger

摘 要：

原 文：http://arxiv.org/pdf/2101.04645v1

---

综述

Survey

[29]

A Brief Survey of Associations Between Meta-Learning and General AI

Huimin Peng

摘 要：

原 文：http://arxiv.org/pdf/2101.04283v1

---

[30]

A Survey of Privacy-Preserving Techniques for Encrypted Traffic Inspection over Network Middleboxes

Geong Sen Poh, Dinil Mon Divakaran, Hoon Wei Lim, Jianting Ning, Achintya Desai

摘 要：

原 文：http://arxiv.org/pdf/2101.04338v1

---

[31]

Hyperbolic Deep Neural Networks: A Survey

Wei Peng, Tuomas Varanka, Abdelrahman Mostafa, Henglin Shi, Guoying Zhao

摘 要：

原 文：http://arxiv.org/pdf/2101.04562v1

---

[32]

Surface Electromyography as a Natural Human-Machine Interface: A Review

Mingde Zheng, Michael Crouch, Michael S. Eggleston

摘 要：

原 文：http://arxiv.org/pdf/2101.04658v1

---

平台与工具

Platform & Tool

[33]

FaceX-Zoo: A PyTorh Toolbox for Face Recognition

Jun Wang, Yinglu Liu, Yibo Hu, Hailin Shi, Tao Mei

摘 要：

原 文：http://arxiv.org/pdf/2101.04407v1

---

强化学习

Reinforcement Learning

[34]

Queue-Learning: A Reinforcement Learning Approach for Providing Quality of Service

Majid Raeis, Ali Tizghadam, Alberto Leon-Garcia

摘 要：

原 文：http://arxiv.org/pdf/2101.04627v1

---

推荐系统

Recommendation System

[35]

Neural News Recommendation with Negative Feedback

Chuhan Wu, Fangzhao Wu, Yongfeng Huang, Xing Xie

摘 要：

原 文：http://arxiv.org/pdf/2101.04328v1

---

[36]

Measuring Recommender System Effects with Simulated Users

Sirui Yao, Yoni Halpern, Nithum Thain, Xuezhi Wang, Kang Lee, Flavien Prost, Ed H. Chi, Jilin Chen, Alex Beutel

摘 要：

原 文：http://arxiv.org/pdf/2101.04526v1

---

其他技术

Others

[37]

A Bayesian neural network predicts the dissolution of compact planetary systems

Miles Cranmer, Daniel Tamayo, Hanno Rein, Peter Battaglia, Samuel Hadden, Philip J. Armitage, Shirley Ho, David N. Spergel

摘 要：

原 文：http://arxiv.org/pdf/2101.04117v1

---

点个在看，再下论文~
（密码：6tvc）