By transferring knowledge learned from seen/previous tasks, meta learning aims to generalize well to unseen/future tasks. Existing meta-learning approaches have shown promising empirical performance on various multiclass classification problems, but few provide theoretical analysis on the classifiers' generalization ability on future tasks. In this paper, under the assumption that all classification tasks are sampled from the same meta-distribution, we leverage margin theory and statistical learning theory to establish three margin-based transfer bounds for meta-learning based multiclass classification (MLMC). These bounds reveal that the expected error of a given classification algorithm for a future task can be estimated with the average empirical error on a finite number of previous tasks, uniformly over a class of preprocessing feature maps/deep neural networks (i.e. deep feature embeddings). To validate these bounds, instead of the commonly-used cross-entropy loss, a multi-margin loss is employed to train a number of representative MLMC models. Experiments on three benchmarks show that these margin-based models still achieve competitive performance, validating the practical value of our margin-based theoretical analysis.
Bayesian Meta-Learning with Expert Feedback for Task-Shift Adaptation through Causal Embeddings
Department of Computer Science, Aalto University, Espoo, Finland（Aalto大学计算机科学系）；ELLIS Institute Finland, Espoo, Finland（芬兰ELLIS研究所）；Department of Computer Science, University of Manchester, United Kingdom（曼彻斯特大学计算机科学系）
Current meta-learning approaches focus on learning functional representations of relationships between variables, i.e. on estimating conditional expectations in regression. In many applications, however, we are faced with conditional distributions which cannot be meaningfully summarized using expectation only (due to e.g. multimodality). Hence, we consider the problem of conditional density estimation in the meta-learning setting. We introduce a novel technique for meta-learning which combines neural representation and noise-contrastive estimation with the established literature of conditional…
Automatic speaker verification systems are vulnerable to a variety of access threats, prompting research into the formulation of effective spoofing detection systems to act as a gate to filter out such spoofing attacks. This study introduces a simple attention module to infer 3-dim attention weights for the feature map in a convolutional layer, which then optimizes an energy function to determine each neuron's importance. With the advancement of both voice conversion and speech synthesis technologies, unseen spoofing attacks are constantly emerging to limit spoofing detection system performanc…
Xi’an Jiaotong University（西安交通大学）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；Tsinghua University（清华大学）
We study the problem of node classification on graphs with few-shot novel labels, which has two distinctive properties: (1) There are novel labels to emerge in the graph; (2) The novel labels have only a few representative nodes for training a classifier. The study of this problem is instructive and corresponds to many applications such as recommendations for newly formed groups with only a few users in online social networks. To cope with this problem, we propose a novel Meta Transformed Network Embedding framework (MetaTNE), which consists of three modules: (1) A \emph{structural module} pro…
Sri Sivasubramaniya Nadar College of Engineering（斯里西瓦苏布拉马尼亚·纳达尔工程学院）
Annotated images and ground truth for the diagnosis of rare and novel diseases are scarce. This is expected to prevail, considering the small number of affected patient population and limited clinical expertise to annotate images. Further, the frequently occurring long-tailed class distributions in skin lesion and other disease classification datasets cause conventional training approaches to lead to poor generalization due to biased class priors. Few-shot learning, and meta-learning in general, aim to overcome these issues by aiming to perform well in low data regimes. This paper focuses on i…
We introduce a method to provide vectorial representations of visual classification tasks which can be used to reason about the nature of those tasks and their relations. Given a dataset with ground-truth labels and a loss function defined over those labels, we process images through a "probe network" and compute an embedding based on estimates of the Fisher information matrix associated with the probe network parameters. This provides a fixed-dimensional embedding of the task that is independent of details such as the number of classes and does not require any understanding of the class label…
Gradient-based meta-learning techniques are both widely applicable and proficient at solving challenging few-shot learning and fast adaptation problems. However, they have practical difficulties when operating on high-dimensional parameter spaces in extreme low-data regimes. We show that it is possible to bypass these limitations by learning a data-dependent latent generative representation of model parameters, and performing gradient-based meta-learning in this low-dimensional latent space. The resulting approach, latent embedding optimization (LEO), decouples the gradient-based adaptation pr…
Peking University（北京大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；Queen Mary University of London（伦敦玛丽女王大学）；National University of Singapore（新加坡国立大学）
Few-shot learning (FSL) has attracted increasing attention in recent years but remains challenging, due to the intrinsic difficulty in learning to generalize from a few examples. This paper proposes an adaptive margin principle to improve the generalization ability of metric-based meta-learning approaches for few-shot learning problems. Specifically, we first develop a class-relevant additive margin loss, where semantic similarity between each pair of classes is considered to separate samples in the feature embedding space from similar classes. Further, we incorporate the semantic context amon…
Long-tail learning is the problem of learning under skewed label distributions, which pose a challenge for standard learners. Several recent approaches for the problem have proposed enforcing a suitable margin in logit space. Such techniques are intuitive analogues of the guiding principle behind SVMs, and are equally applicable to linear models and neural models. However, when applied to neural models, such techniques do not explicitly control the geometry of the learned embeddings. This can be potentially sub-optimal, since embeddings for tail classes may be diffuse, resulting in poor genera…
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
In the absence of prior knowledge, ordinal embedding methods obtain new representation for items in a low-dimensional Euclidean space via a set of quadruple-wise comparisons. These ordinal comparisons often come from human annotators, and sufficient comparisons induce the success of classical approaches. However, collecting a large number of labeled data is known as a hard task, and most of the existing work pay little attention to the generalization ability with insufficient samples. Meanwhile, recent progress in large margin theory discloses that rather than just maximizing the minimum margi…
HDR-UK Institute of Health Informatics（HDR-UK健康信息学研究所）；University College London（伦敦大学学院）
Learning knowledge representation is an increasingly important technology that supports a variety of machine learning related applications. However, the choice of hyperparameters is seldom justified and usually relies on exhaustive search. Understanding the effect of hyperparameter combinations on embedding quality is crucial to avoid the inefficient process and enhance practicality of vector representation methods. We evaluate the effects of distinct values for the margin parameter focused on translational embedding representation models for multi-relational categorized data. We assess the ma…
Guangzhou Huya Technology Co., Ltd（广州虎牙科技有限公司）；University of Oxford（牛津大学）
Researches using margin based comparison loss demonstrate the effectiveness of penalizing the distance between face feature and their corresponding class centers. Despite their popularity and excellent performance, they do not explicitly encourage the generic embedding learning for an open set recognition problem. In this paper, we analyse margin based softmax loss in probability view. With this perspective, we propose two general principles: 1) monotonic decreasing and 2) margin probability penalty, for designing new margin loss functions. Unlike methods optimized with single comparison metri…
University of the Basque Country (UPV/EHU)（巴斯克大学）；Facebook AI Research（Facebook人工智能研究院）
Machine translation is highly sensitive to the size and quality of the training data, which has led to an increasing interest in collecting and filtering large parallel corpora. In this paper, we propose a new method for this task based on multilingual sentence embeddings. In contrast to previous approaches, which rely on nearest neighbor retrieval with a hard threshold over cosine similarity, our proposed method accounts for the scale inconsistencies of this measure, considering the margin between a given sentence pair and its closest candidates instead. Our experiments show large improvement…
Nexar；UC Berkeley（加州大学伯克利分校）；UC San Diego（加州大学圣迭戈分校）
Metric learning seeks perceptual embeddings where visually similar instances are close and dissimilar instances are apart, but learned representations can be sub-optimal when the distribution of intra-class samples is diverse and distinct sub-clusters are present. Although theoretically with optimal assumptions, margin-based losses such as the triplet loss and margin loss have a diverse family of solutions. We theoretically prove and empirically show that under reasonable noise assumptions, margin-based losses tend to project all samples of a class with various modes onto a single point in the…
University of Bonn（波恩大学）；Fraunhofer IAIS（弗劳恩霍夫智能分析与信息系统研究所）
Translation-based embedding models have gained significant attention in link prediction tasks for knowledge graphs. TransE is the primary model among translation-based embeddings and is well-known for its low complexity and high efficiency. Therefore, most of the earlier works have modified the score function of the TransE approach in order to improve the performance of link prediction tasks. Nevertheless, proven theoretically and experimentally, the performance of TransE strongly depends on the loss function. Margin Ranking Loss (MRL) has been one of the earlier loss functions which is widely…
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）；Adobe Research（奥多比研究院）
Classifying large-scale image data into object categories is an important problem that has received increasing research attention. Given the huge amount of data, non-parametric approaches such as nearest neighbor classifiers have shown promising results, especially when they are underpinned by a learned distance or similarity measurement. Although metric learning has been well studied in the past decades, most existing algorithms are impractical to handle large-scale data sets. In this paper, we present an image similarity learning method that can scale well in both the number of images and th…
FHGE: A Fast Heterogeneous Graph Embedding with Ad-hoc Meta-paths
School of Computer Science, Fudan University（复旦大学计算机科学学院）；School of Software, Fudan University（复旦大学软件学院）；Shanghai Key Laboratory of Data Science（上海数据科学重点实验室）
Speaker diarisation systems nowadays use embeddings generated from speech segments in a bottleneck layer, which are needed to be discriminative for unseen speakers. It is well-known that large-margin training can improve the generalisation ability to unseen data, and its use in such open-set problems has been widespread. Therefore, this paper introduces a general approach to the large-margin softmax loss without any approximations to improve the quality of speaker embeddings for diarisation. Furthermore, a novel and simple way to stabilise training, when large-margin softmax is used, is propos…
Given multiple source word embeddings learnt using diverse algorithms and lexical resources, meta word embedding learning methods attempt to learn more accurate and wide-coverage word embeddings. Prior work on meta-embedding has repeatedly discovered that simple vector concatenation of the source embeddings to be a competitive baseline. However, it remains unclear as to why and when simple vector concatenation can produce accurate meta-embeddings. We show that weighted concatenation can be seen as a spectrum matching operation between each source embedding and the meta-embedding, minimising th…
University of Illinois, Urbana Champaign（伊利诺伊大学厄巴纳-香槟分校）
In this work, we propose to study the utility of different meta-graphs, as well as how to simultaneously leverage multiple meta-graphs for HIN embedding in an unsupervised manner. Motivated by prolific research on homogeneous networks, especially spectral graph theory, we firstly conduct a systematic empirical study on the spectrum and embedding quality of different meta-graphs on multiple HINs, which leads to an efficient method of meta-graph assessment. It also helps us to gain valuable insight into the higher-order organization of HINs and indicates a practical way of selecting useful embed…
The role of data-induced randomness in quantum machine learning classification tasks
Barcelona Supercomputing Center（巴塞罗那超级计算中心）；Universitat de Barcelona（巴塞罗那大学）；Universiteit Leiden（莱顿大学）；Lorentz Instituut（洛伦兹研究所）；Honda Research Institute Europe GmbH（本田欧洲研究院）
POSTECH（浦项科技大学）；Graduate School of AI POSTECH（浦项科技大学人工智能研究生院）
Attribute-based person search is the task of finding person images that are best matched with a set of text attributes given as query. The main challenge of this task is the large modality gap between attributes and images. To reduce the gap, we present a new loss for learning cross-modal embeddings in the context of attribute-based person search. We regard a set of attributes as a category of people sharing the same traits. In a joint embedding space of the two modalities, our loss pulls images close to their person categories for modality alignment. More importantly, it pushes apart a pair o…
Bosch Center for Artificial Intelligence（博世人工智能中心）；Saarland University（萨尔大学）
Combining several embeddings typically improves performance in downstream tasks as different embeddings encode different information. It has been shown that even models using embeddings from transformers still benefit from the inclusion of standard word embeddings. However, the combination of embeddings of different types and dimensions is challenging. As an alternative to attention-based meta-embeddings, we propose feature-based adversarial meta-embeddings (FAME) with an attention function that is guided by features reflecting word-specific properties, such as shape and frequency, and show th…
Ensembling word embeddings to improve distributed word representations has shown good success for natural language processing tasks in recent years. These approaches either carry out straightforward mathematical operations over a set of vectors or use unsupervised learning to find a lower-dimensional representation. This work compares meta-embeddings trained for different losses, namely loss functions that account for angular distance between the reconstructed embedding and the target and those that account normalized distances based on the vector length. We argue that meta-embeddings are bett…
The University of Liverpool（利物浦大学）；Japan Advanced Institute of Science and Technology（日本先进科学技术大学）；National Institute of Informatics（日本国立信息学研究所）；Japan Science and Technology Agency, ERATO, Kawarabayashi Large Graph Project（日本科学技术振兴机构 ERATO 河原林大型图项目）
Distributed word embeddings have shown superior performances in numerous Natural Language Processing (NLP) tasks. However, their performances vary significantly across different tasks, implying that the word embeddings learnt by those methods capture complementary aspects of lexical semantics. Therefore, we believe that it is important to combine the existing word embeddings to produce more accurate and complete \emph{meta-embeddings} of words. For this purpose, we propose an unsupervised locally linear meta-embedding learning method that takes pre-trained word embeddings as the input, and pro…
We propose a geometric framework for learning meta-embeddings of words from different embedding sources. Our framework transforms the embeddings into a common latent space, where, for example, simple averaging of different embeddings (of a given word) is more amenable. The proposed latent space arises from two particular geometric transformations - the orthogonal rotations and the Mahalanobis metric scaling. Empirical results on several word similarity and word analogy benchmarks illustrate the efficacy of the proposed framework.
Word embeddings have been shown to benefit from ensambling several word embedding sources, often carried out using straightforward mathematical operations over the set of word vectors. More recently, self-supervised learning has been used to find a lower-dimensional representation, similar in size to the individual word embeddings within the ensemble. However, these methods do not use the available manually labeled datasets that are often used solely for the purpose of evaluation. We propose to reconstruct an ensemble of word embeddings as an auxiliary task that regularises a main task while b…
University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；Amazon（亚马逊）；Northwestern University（西北大学）
Distributed representations of medical concepts have been used to support downstream clinical tasks recently. Electronic Health Records (EHR) capture different aspects of patients' hospital encounters and serve as a rich source for augmenting clinical decision making by learning robust medical concept embeddings. However, the same medical concept can be recorded in different modalities (e.g., clinical notes, lab results)-with each capturing salient information unique to that modality-and a holistic representation calls for relevant feature ensemble from all information sources. We hypothesize …
University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；Cornell University（康奈尔大学）；The University of Hong Kong（香港大学）；Facebook（脸书）
Meta-graph is currently the most powerful tool for similarity search on heterogeneous information networks,where a meta-graph is a composition of meta-paths that captures the complex structural information. However, current relevance computing based on meta-graph only considers the complex structural information, but ignores its embedded meta-paths information. To address this problem, we proposeMEta-GrAph-based network embedding models, called MEGA and MEGA++, respectively. The MEGA model uses normalized relevance or similarity measures that are derived from a meta-graph and its embedded meta…
University Of Delhi（德里大学）；National Informatics Center（国家信息中心）
Metaphors are ubiquitous in natural language, and their detection plays an essential role in many natural language processing tasks, such as language understanding, sentiment analysis, etc. Most existing approaches for metaphor detection rely on complex, hand-crafted and fine-tuned feature pipelines, which greatly limit their applicability. In this work, we present an end-to-end method composed of deep contextualized word embeddings, bidirectional LSTMs and multi-head attention mechanism to address the task of automatic metaphor detection. Our method, unlike many other existing approaches, req…
University College London（伦敦大学学院）；École Polytechnique（巴黎综合理工学院）
A new computationally efficient dependence measure, and an adaptive statistical test of independence, are proposed. The dependence measure is the difference between analytic embeddings of the joint distribution and the product of the marginals, evaluated at a finite set of locations (features). These features are chosen so as to maximize a lower bound on the test power, resulting in a test that is data-efficient, and that runs in linear time (with respect to the sample size n). The optimized features can be interpreted as evidence to reject the null hypothesis, indicating regions in the joint …
Heterogeneous information network (HIN) embedding has recently attracted much attention due to its effectiveness in dealing with the complex heterogeneous data. Meta path, which connects different object types with various semantic meanings, is widely used by existing HIN embedding works. However, several challenges have not been addressed so far. First, different meta paths convey different semantic meanings, while existing works assume that all nodes share same weights for meta paths and ignore the personalized preferences of different nodes on different meta paths. Second, given a meta path…
Heterogeneous information networks(HINs) become popular in recent years for its strong capability of modelling objects with abundant information using explicit network structure. Network embedding has been proved as an effective method to convert information networks into lower-dimensional space, whereas the core information can be well preserved. However, traditional network embedding algorithms are sub-optimal in capturing rich while potentially incompatible semantics provided by HINs. To address this issue, a novel meta-path-based HIN representation learning framework named mSHINE is design…
Word Representations form the core component for almost all advanced Natural Language Processing (NLP) applications such as text mining, question-answering, and text summarization, etc. Over the last two decades, immense research is conducted to come up with one single model to solve all major NLP tasks. The major problem currently is that there are a plethora of choices for different NLP tasks. Thus for NLP practitioners, the task of choosing the right model to be used itself becomes a challenge. Thus combining multiple pre-trained word embeddings and forming meta embeddings has become a viab…
Meta-embedding (ME) learning is an emerging approach that attempts to learn more accurate word embeddings given existing (source) word embeddings as the sole input. Due to their ability to incorporate semantics from multiple source embeddings in a compact manner with superior performance, ME learning has gained popularity among practitioners in NLP. To the best of our knowledge, there exist no prior systematic survey on ME learning and this paper attempts to fill this need. We classify ME learning methods according to multiple factors such as whether they (a) operate on static or contextualise…
International Institute of Information Technology - Hyderabad (IIIT-Hyderabad)（海得拉巴国际信息技术学院（IIIT-Hyderabad））
Code-mixing(CM) is a frequently observed phenomenon that uses multiple languages in an utterance or sentence. CM is mostly practiced on various social media platforms and in informal conversations. Sentiment analysis (SA) is a fundamental step in NLP and is well studied in the monolingual text. Code-mixing adds a challenge to sentiment analysis due to its non-standard representations. This paper proposes a meta embedding with a transformer method for sentiment analysis on the Dravidian code-mixed dataset. In our method, we used meta embeddings to capture rich text representations. We used the …
Integrating Meta-Features with Knowledge Graph Embeddings for Meta-Learning
Bosch Center for Artificial Intelligence（博世人工智能中心）；University of Mannheim（曼海姆大学）；KU Leuven（比利时库勒韦恩大学）；Leuven.AI - KU Leuven Institute for AI（勒维恩人工智能-库勒韦恩人工智能研究所）；Flanders Make（弗拉芒制造）；Univesity of Oslo（奥斯陆大学）
Click-through rate (CTR) prediction is one of the most central tasks in online advertising systems. Recent deep learning-based models that exploit feature embedding and high-order data nonlinearity have shown dramatic successes in CTR prediction. However, these models work poorly on cold-start ads with new IDs, whose embeddings are not well learned yet. In this paper, we propose Graph Meta Embedding (GME) models that can rapidly learn how to generate desirable initial embeddings for new ad IDs based on graph neural networks and meta learning. Previous works address this problem from the new ad…
University of Waterloo（滑铁卢大学）；Aalto University（阿尔托大学）
We review the current schemes of text-image matching models and propose improvements for both training and inference. First, we empirically show limitations of two popular loss (sum and max-margin loss) widely used in training text-image embeddings and propose a trade-off: a kNN-margin loss which 1) utilizes information from hard negatives and 2) is robust to noise as all $K$-most hardest samples are taken into account, tolerating \emph{pseudo} negatives and outliers. Second, we advocate the use of Inverted Softmax (\textsc{Is}) and Cross-modal Local Scaling (\textsc{Csls}) during inference to…
Zhejiang University（浙江大学）；Huawei Technologies Co., Ltd.（华为技术有限公司）；State Key Laboratory of Media Convergence Production Technology and Systems（媒体融合生产技术与系统国家重点实验室）；ZJU-Hangzhou Global Scientific and Technological Innovation Center（浙江大学杭州国际科创中心）；Alibaba-Zhejiang University Joint Institute of Frontier Technologies（阿里巴巴-浙江大学前沿技术联合研究院）
Knowledge graphs (KGs) consisting of a large number of triples have become widespread recently, and many knowledge graph embedding (KGE) methods are proposed to embed entities and relations of a KG into continuous vector spaces. Such embedding methods simplify the operations of conducting various in-KG tasks (e.g., link prediction) and out-of-KG tasks (e.g., question answering). They can be viewed as general solutions for representing KGs. However, existing KGE methods are not applicable to inductive settings, where a model trained on source KGs will be tested on target KGs with entities unsee…
Despite significant progress, deep reinforcement learning (RL) suffers from data-inefficiency and limited generalization. Recent efforts apply meta-learning to learn a meta-learner from a set of RL tasks such that a novel but related task could be solved quickly. Though specific in some ways, different tasks in meta-RL are generally similar at a high level. However, most meta-RL methods do not explicitly and adequately model the specific and shared information among different tasks, which limits their ability to learn training tasks and to generalize to novel tasks. In this paper, we propose t…
Beijing Advanced Innovation Center for Big Data and Brain Computing（北京大数据与脑计算高级创新中心）；Beihang University（北京航空航天大学）；HKUST（香港科技大学）；UIUC（伊利诺伊大学厄巴纳-香槟分校）
Heterogeneous information network (HIN) embedding has gained increasing interests recently. However, the current way of random-walk based HIN embedding methods have paid few attention to the higher-order Markov chain nature of meta-path guided random walks, especially to the stationarity issue. In this paper, we systematically formalize the meta-path guided random walk as a higher-order Markov chain process, and present a heterogeneous personalized spacey random walk to efficiently and effectively attain the expected stationary distribution among nodes. Then we propose a generalized scalable f…
Nuance Communications（Nuance通信公司）；Brno University of Technology（布尔诺理工大学）；University of Nottingham（诺丁汉大学）；Omilia Conversational Intelligence（Omilia对话智能公司）
Embeddings in machine learning are low-dimensional representations of complex input patterns, with the property that simple geometric operations like Euclidean distances and dot products can be used for classification and comparison tasks. The proposed meta-embeddings are special embeddings that live in more general inner product spaces. They are designed to propagate uncertainty to the final output in speaker recognition and similar applications. The familiar Gaussian PLDA model (GPLDA) can be re-formulated as an extractor for Gaussian meta-embeddings (GMEs), such that likelihood ratio scores…
Universidad de la República（共和国大学）；Duke University（杜克大学）
Deep neural networks trained using a softmax layer at the top and the cross-entropy loss are ubiquitous tools for image classification. Yet, this does not naturally enforce intra-class similarity nor inter-class margin of the learned deep representations. To simultaneously achieve these two goals, different solutions have been proposed in the literature, such as the pairwise or triplet losses. However, such solutions carry the extra task of selecting pairs or triplets, and the extra computational burden of computing and learning for many combinations of them. In this paper, we propose a plug-a…
In this thesis, we study the problem of feature learning on heterogeneous knowledge graphs. These features can be used to perform tasks such as link prediction, classification and clustering on graphs. Knowledge graphs provide rich semantics encoded in the edge and node types. Meta-paths consist of these types and abstract paths in the graph. Until now, meta-paths can only be used as categorical features with high redundancy and are therefore unsuitable for machine learning models. We propose meta-path embeddings to solve this problem by learning semantical and compact vector representations o…
