Discriminative Learning of Similarity and Group Equivariant Representations
Toyota Technological Institute at Chicago(芝加哥丰田技术研究所);The University of Chicago(芝加哥大学);Fermilab(费米实验室)
Shubhendu Trivedi
备注:
PhD thesis, September 2018 [Previous version had a compile error that was spotted recently, which is fixed. The uploaded version is the final thesis that was submitted in September 2018]
One of the most fundamental problems in machine learning is to compare examples: Given a pair of objects we want to return a value which indicates degree of (dis)similarity. Similarity is often task specific, and pre-defined distances can perform poorly, leading to work in metric learning. However, being able to learn a similarity-sensitive distance function also presupposes access to a rich, discriminative representation for the objects at hand. In this dissertation we present contributions towards both ends. In the first part of the thesis, assuming good representations for the data, we present a formulation for metric learning that makes a more direct attempt to optimize for the k-NN accuracy as compared to prior work. We also present extensions of this formulation to metric learning for kNN regression, asymmetric similarity learning and discriminative learning of Hamming distance. In the second part, we consider a situation where we are on a limited computational budget i.e. optimizing over a space of possible metrics would be infeasible, but access to a label aware distance metric is still desirable. We present a simple, and computationally inexpensive approach for estimating a well motivated metric that relies only on gradient estimates, discussing theoretical and experimental results. In the final part, we address representational issues, considering group equivariant convolutional neural networks (GCNNs). Equivariance to symmetry transformations is explicitly encoded in GCNNs; a classical CNN being the simplest example. In particular, we present a SO(3)-equivariant neural network architecture for spherical data, that operates entirely in Fourier space, while also providing a formalism for the design of fully Fourier neural networks that are equivariant to the action of any continuous compact group.
Discriminative Similarity for Clustering and Semi-Supervised Learning
Snap Research(Snap 研究院);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Microsoft Research(微软研究院);National University of Singapore(新加坡国立大学);Beckman Institute, University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校贝克曼研究所)
Graph Structure Refinement with Energy-based Contrastive Learning
Beihang University(北京航空航天大学);Postdoctoral Research Station at China RongTong Academy of Sciences Group Corporation Limited(中国融通集团博士后科研工作站);Eastern Institute of Technology(宁波工程学院);Ningbo Institute of Digital Twin, Eastern Institute of Technology(宁波工程学院宁波数字孪生研究院)
When Hard Negatives Hurt: Bridging the Generative-Discriminative Gap in Hard Negative Synthesis for Retrieval
Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院);Huawei Technologies Co., Ltd.(华为技术有限公司);City University of Hong Kong(香港城市大学);School of Cyber Science and Technology, Sun Yat-sen University(中山大学信息科学与技术学院);School of Intelligence Science and Technology, Nanjing University(南京大学智能科学与技术学院);The Hong Kong University of Science and Technology(香港科学与技术大学);Huawei Noah’s Ark Lab(华为诺亚实验室)
Auto-weighted low-rank representation for clustering
Institute of Information Science, Beijing Jiaotong University(北京交通大学信息科学研究所);Beijing Key Laboratory of Advanced Information Science and Network Technology(北京先进信息科学与网络技术重点实验室);Department of Computer Science and Technology, Tsinghua University(清华大学计算机科学与技术系)
Learning the Relation between Similarity Loss and Clustering Loss in Self-Supervised Learning
Nanjing University(南京大学);Southeast University(东南大学);Purple Mountain Laboratories(紫金山实验室);Amazon.com L.L.C.(亚马逊有限责任公司);Alibaba Group(阿里巴巴集团);The Hong Kong University of Science and Technology(香港科技大学);Southern Methodist University(南卫理公会大学)
我们研究了深度神经网络在与文本无关的说话人识别任务中的性能。我们证明,在分类神经网络的最后一个分类层使用角softmax激活,而不是一个简单的softmax激活允许训练一个更广义的判别扬声器嵌入提取器。余弦相似度是在该嵌入空间中进行说话人确认的有效度量。我们还解决了选择一个架构的提取器的问题。我们发现,具有残留帧级连接的深度网络优于宽但相对较浅的架构。本文还提出了一些改进以前的基于DNN的提取器系统,以提高说话人识别的准确性。我们表明,区别训练的相似性度量学习方法优于标准的LDA-PLDA方法作为嵌入后端。在Speakers in the Wild和NIST SRE 2016评估集上获得的结果证明了所提出的系统在处理接近现实生活条件时的鲁棒性。