Network representation learning (NRL) is a powerful technique for learning low-dimensional vector representation of high-dimensional and sparse graphs. Most studies explore the structure and metadata associated with the graph using random walks and employ an unsupervised or semi-supervised learning schemes. Learning in these methods is context-free, because only a single representation per node is learned. Recently studies have argued on the sufficiency of a single representation and proposed a context-sensitive approach that proved to be highly effective in applications such as link prediction and ranking.
However, most of these methods rely on additional textual features that require RNNs or CNNs to capture high-level features or rely on a community detection algorithm to identify multiple contexts of a node.
In this study, without requiring additional features nor a community detection algorithm, we propose a novel context-sensitive algorithm called GAP that learns to attend on different parts of a node's neighborhood using attentive pooling networks. We show the efficacy of GAP using three real-world datasets on link prediction and node clustering tasks and compare it against 10 popular and state-of-the-art (SOTA) baselines. GAP consistently outperforms them and achieves up to ~9% and ~20% gain over the best performing methods on link prediction and clustering tasks, respectively.
In this paper, we introduce a novel language identification system based on conformer layers. We propose an attentive temporal pooling mechanism to allow the model to carry information in long-form audio via a recurrent form, such that the inference can be performed in a streaming fashion. Additionally, we investigate two domain adaptation approaches to allow adapting an existing language identification model without retraining the model parameters for a new domain. We perform a comparative study of different model topologies under different constraints of model size, and find that conformer-b…
Huazhong University of Science and Technology（华中科技大学）；IBM T.J. Watson Research Center（IBM T.J. Watson 研究中心）；Northwestern University（西北大学）；AI Foundations, IBM Research（IBM 研究院 AI 基础部门）
Person Re-Identification (person re-id) is a crucial task as its applications in visual surveillance and human-computer interaction. In this work, we present a novel joint Spatial and Temporal Attention Pooling Network (ASTPN) for video-based person re-identification, which enables the feature extractor to be aware of the current input video sequences, in a way that interdependency from the matching items can directly influence the computation of each other's representation. Specifically, the spatial pooling layer is able to select regions from each frame, while the attention temporal pooling …
Dalian University of Technology（大连理工大学）；Tianjin University（天津大学）
For video recognition task, a global representation summarizing the whole contents of the video snippets plays an important role for the final performance. However, existing video architectures usually generate it by using a simple, global average pooling (GAP) method, which has limited ability to capture complex dynamics of videos. For image recognition task, there exist evidences showing that covariance pooling has stronger representation ability than GAP. Unfortunately, such plain covariance pooling used in image recognition is an orderless representative, which cannot model spatio-temporal…
IBM Watson（IBM沃森）；T.J. Watson Research Center（T.J.沃森研究中心）
In this work, we propose Attentive Pooling (AP), a two-way attention mechanism for discriminative model training. In the context of pair-wise ranking or classification with neural networks, AP enables the pooling layer to be aware of the current input pair, in a way that information from the two input items can directly influence the computation of each other's representations. Along with such representations of the paired inputs, AP jointly learns a similarity measure over projected segments (e.g. trigrams) of the pair, and subsequently, derives the corresponding attention vector for each inp…
Efficient custom pooling techniques that can aggressively trim the dimensions of a feature map and thereby reduce inference compute and memory footprint for resource-constrained computer vision applications have recently gained significant traction. However, prior pooling works extract only the local context of the activation maps, limiting their effectiveness. In contrast, we propose a novel non-local self-attentive pooling method that can be used as a drop-in replacement to the standard pooling layers, such as max/average pooling or strided convolution. The proposed self-attention module use…
Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification
University of Kassel（卡塞尔大学）；Fraunhofer IEE（弗劳恩霍夫研究所）；Ghent University（根特大学）；ML and Systems Biology, MPI of Biochemistry（生物化学Max Planck研究所）；INRIA Montpellier（蒙彼利埃INRIA）
This memo describes NTR/TSU winning submission for Low Resource ASR challenge at Dialog2021 conference, language identification track. Spoken Language Identification (LID) is an important step in a multilingual Automated Speech Recognition (ASR) system pipeline. Traditionally, the ASR task requires large volumes of labeled data that are unattainable for most of the world's languages, including most of the languages of Russia. In this memo, we show that a convolutional neural network with a Self-Attentive Pooling layer shows promising results in low-resource setting for the language identificat…
Department of ECE and the Visual Narrative Initiative, North Carolina State University（北卡罗来纳州立大学电气与计算机工程系及视觉叙事研究所）
Image synthesis and image-to-image translation are two important generative learning tasks. Remarkable progress has been made by learning Generative Adversarial Networks (GANs)~\cite{goodfellow2014generative} and cycle-consistent GANs (CycleGANs)~\cite{zhu2017unpaired} respectively. This paper presents a method of learning Spatial Pyramid Attentive Pooling (SPAP) which is a novel architectural unit and can be easily integrated into both generators and discriminators in GANs and CycleGANs. The proposed SPAP integrates Atrous spatial pyramid~\cite{chen2018deeplab}, a proposed cascade attention m…
Guangdong Polytechnic Normal University（广东技术师范大学）；Guangdong University of Technology（广东工业大学）
With higher-order neighborhood information of graph network, the accuracy of graph representation learning classification can be significantly improved. However, the current higher order graph convolutional network has a large number of parameters and high computational complexity. Therefore, we propose a Hybrid Lower order and Higher order Graph convolutional networks (HLHG) learning model, which uses weight sharing mechanism to reduce the number of network parameters. To reduce computational complexity, we propose a novel fusion pooling layer to combine the neighborhood information of high o…
Rochester Institute of Technology（罗切斯特理工学院）；Appen Machine Learning Team（澳鹏机器学习团队）
Supervised machine learning often requires human-annotated data. While annotator disagreement is typically interpreted as evidence of noise, population-level label distribution learning (PLDL) treats the collection of annotations for each data item as a sample of the opinions of a population of human annotators, among whom disagreement may be proper and expected, even with no noise present. From this perspective, a typical training set may contain a large number of very small-sized samples, one for each data item, none of which, by itself, is large enough to be considered representative of the…
School of Information Management for Law（法治信息管理学院）；China University of Political Science and Law（中国政法大学）；China Coal Research Institute（煤炭科学研究总院）
Time series classification problems exist in many fields and have been explored for a couple of decades. However, they still remain challenging, and their solutions need to be further improved for real-world applications in terms of both accuracy and efficiency. In this paper, we propose a hybrid neural architecture, called Self-Attentive Recurrent Convolutional Networks (SARCoN), to learn multi-faceted representations for univariate time series. SARCoN is the synthesis of long short-term memory networks with self-attentive mechanisms and Fully Convolutional Networks, which work in parallel to…
Nanyang Technological University（南洋理工大学）；Institute of High Performance Computing（高性能计算研究所）
Graph Neural Networks (GNN) has demonstrated the superior performance in many challenging applications, including the few-shot learning tasks. Despite its powerful capacity to learn and generalize the model from few samples, GNN usually suffers from severe over-fitting and over-smoothing as the model becomes deep, which limit the scalability. In this work, we propose a novel Attentive GNN to tackle these challenges, by incorporating a triple-attention mechanism, i.e. node self-attention, neighborhood attention, and layer memory attention. We explain why the proposed attentive modules can impro…
University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；Quebec AI Institute (Mila)（魁北克人工智能研究所（Mila））；Amazon Alexa AI（亚马逊Alexa人工智能部门）
Graph neural networks (GNNs) have been shown to possess strong representation power, which can be exploited for downstream prediction tasks on graph-structured data, such as molecules and social networks. They typically learn representations by aggregating information from the $K$-hop neighborhood of individual vertices or from the enumerated walks in the graph. Prior studies have demonstrated the effectiveness of incorporating weighting schemes into GNNs; however, this has been primarily limited to $K$-hop neighborhood GNNs so far. In this paper, we aim to design an algorithm incorporating we…
Graph-based Alignment and Uniformity for Recommendation
University of Illinois Chicago（伊利诺伊大学芝加哥分校）；Salesforce AI Research（赛富时人工智能研究院）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；University of Electronic Science and Technology of China（电子科技大学）
In general, a self-attention mechanism has been applied for speaker embedding encoding. Previous studies focused on training the self-attention in a high-level layer, such as the last pooling layer. However, the effect of low-level features was reduced in the speaker embedding encoding. Therefore, we propose masked cross self-attentive encoding (MCSAE) using ResNet. It focuses on the features of both high-level and lowlevel layers. Based on multi-layer aggregation, the output features of each residual layer are used for the MCSAE. In the MCSAE, cross self-attention module is trained the interd…
University of Hong Kong（香港大学）；MEGVII Technology（旷视科技）；University of Edinburgh（爱丁堡大学）；LunarAI
In this paper, we tackle the problem of learning visual representations from unlabeled scene-centric data. Existing works have demonstrated the potential of utilizing the underlying complex structure within scene-centric data; still, they commonly rely on hand-crafted objectness priors or specialized pretext tasks to build a learning framework, which may harm generalizability. Instead, we propose contrastive learning from data-driven semantic slots, namely SlotCon, for joint semantic grouping and representation learning. The semantic grouping is performed by assigning pixels to a set of learna…
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；Alibaba Group（阿里巴巴集团）
Traffic forecasting is of great importance to transportation management and public safety, and very challenging due to the complicated spatial-temporal dependency and essential uncertainty brought about by the road network and traffic conditions. Latest studies mainly focus on modeling the spatial dependency by utilizing graph convolutional networks (GCNs) throughout a fixed weighted graph. However, edges, i.e., the correlations between pair-wise nodes, are much more complicated and interact with each other. In this paper, we propose the Multi-Range Attentive Bicomponent GCN (MRA-BGCN), a nove…
Shanghai Jiao Tong University（上海交通大学）；École Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院（EPFL））
With the advent of data science, the analysis of network or graph data has become a very timely research problem. A variety of recent works have been proposed to generalize neural networks to graphs, either from a spectral graph theory or a spatial perspective. The majority of these works however focus on adapting the convolution operator to graph representation. At the same time, the pooling operator also plays an important role in distilling multiscale and hierarchical representations but it has been mostly overlooked so far. In this paper, we propose a parameter-free pooling operator, calle…
Seoul National University（首尔国立大学）；AIGENDRUG Co. Ltd.（AIGENDRUG有限公司）
While graph neural networks (GNNs) have been successful for node classification tasks and link prediction tasks in graph, learning graph-level representations still remains a challenge. For the graph-level representation, it is important to learn both representation of neighboring nodes, i.e., aggregation, and graph structural information. A number of graph pooling methods have been developed for this goal. However, most of the existing pooling methods utilize k-hop neighborhood without considering explicit structural information in a graph. In this paper, we propose Structure Prototype Guided…
Georgia State University（佐治亚州立大学）；University of Wisconsin–Madison（威斯康星大学麦迪逊分校）
Graph Neural networks (GNNs) have recently become a powerful technique for many graph-related tasks including graph classification. Current GNN models apply different graph pooling methods that reduce the number of nodes and edges to learn the higher-order structure of the graph in a hierarchical way. All these methods primarily rely on the one-hop neighborhood. However, they do not consider the higher- order structure of the graph. In this work, we propose a multi-channel Motif-based Graph Pooling method named (MPool) captures the higher-order graph structure with motif and local and global g…
Ant Group（蚂蚁集团）；Wuhan University（武汉大学）；Swinburne University of Technology（斯威本科技大学）
Heterogeneous graph neural network has unleashed great potential on graph representation learning and shown superior performance on downstream tasks such as node classification and clustering. Existing heterogeneous graph learning networks are primarily designed to either rely on pre-defined meta-paths or use attention mechanisms for type-specific attentive message propagation on different nodes/edges, incurring many customization efforts and computational costs. To this end, we design a relation-centered Pooling and Convolution for Heterogeneous Graph learning Network, namely PC-HGN, to enabl…
Generalized Stock Price Prediction for Multiple Stocks Combined with News Fusion
Graduate Institute of Electrical Engineering, National Taiwan University（国立台湾大学电子工程研究所）；Institute of Information Science, Academia Sinica（学术院信息科学研究所）；United Link Co., Ltd.（联合链接公司）；University of Washington（华盛顿大学）；National Tsing Hua University（国立清华大学）
Convolution and pooling are the key operations to learn hierarchical representation for graph classification, where more expressive $k$-order($k>1$) method requires more computation cost, limiting the further applications. In this paper, we investigate the strategy of selecting $k$ via neighborhood information gain and propose light $k$-order convolution and pooling requiring fewer parameters while improving the performance. Comprehensive and fair experiments through six graph classification benchmarks show: 1) the performance improvement is consistent to the $k$-order information gain. 2) the…
University of Technology Sydney（悉尼科技大学）；Monash University（莫纳什大学）
Graph convolutional networks (GCNs) have recently become one of the most powerful tools for graph analytics tasks in numerous applications, ranging from social networks and natural language processing to bioinformatics and chemoinformatics, thanks to their ability to capture the complex relationships between concepts. At present, the vast majority of GCNs use a neighborhood aggregation framework to learn a continuous and compact vector, then performing a pooling operation to generalize graph embedding for the classification task. These approaches have two disadvantages in the graph classificat…
Shanghai Jiao Tong University（上海交通大学）；Mitsubishi Electric Laboratories（三菱电机实验室）；University of Technology, Sydney（悉尼科技大学）
We propose a novel graph cross network (GXN) to achieve comprehensive feature learning from multiple scales of a graph. Based on trainable hierarchical representations of a graph, GXN enables the interchange of intermediate features across scales to promote information flow. Two key ingredients of GXN include a novel vertex infomax pooling (VIPool), which creates multiscale graphs in a trainable manner, and a novel feature-crossing layer, enabling feature interchange across scales. The proposed VIPool selects the most informative subset of vertices based on the neural estimation of mutual info…
Shanghai Jiao Tong University（上海交通大学）；University of California, Los Angeles（加州大学洛杉矶分校）；Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）
A collection of approaches based on graph convolutional networks have proven success in skeleton-based action recognition by exploring neighborhood information and dense dependencies between intra-frame joints. However, these approaches usually ignore the spatial-temporal global context as well as the local relation between inter-frame and intra-frame. In this paper, we propose a focusing and diffusion mechanism to enhance graph convolutional networks by paying attention to the kinematic dependence of articulated human pose in a frame and their implicit dependencies over frames. In the focusin…
Shanghai Jiao Tong University（上海交通大学）；SenseTime Research（商汤科技研究院）；Qing Yuan Research Institute, Shanghai Jiao Tong University（上海交通大学清源研究院）
Scalability is an important consideration for deep graph neural networks. Inspired by the conventional pooling layers in CNNs, many recent graph learning approaches have introduced the pooling strategy to reduce the size of graphs for learning, such that the scalability and efficiency can be improved. However, these pooling-based methods are mainly tailored to a single graph-level task and pay more attention to local information, limiting their performance in multi-task settings which often require task-specific global information. In this paper, departure from these pooling-based efforts, we …
Graph neural networks (GNN) have been proven to be mature enough for handling graph-structured data on node-level graph representation learning tasks. However, the graph pooling technique for learning expressive graph-level representation is critical yet still challenging. Existing pooling methods either struggle to capture the local substructure or fail to effectively utilize high-order dependency, thus diminishing the expression capability. In this paper we propose HAP, a hierarchical graph-level representation learning framework, which is adaptively sensitive to graph structures, i.e., HAP …
Convolutional Neural Networks (CNNs) are artificial learning systems typically based on two operations: convolution, which implements feature extraction through filtering, and pooling, which implements dimensionality reduction. The impact of pooling in the classification performance of the CNNs has been highlighted in several previous works, and a variety of alternative pooling operators have been proposed. However, only a few of them tackle with the uncertainty that is naturally propagated from the input layer to the feature maps of the hidden layers through convolutions. In this paper we pre…
Equivariant Spatio-Temporal Attentive Graph Networks to Simulate Physical Dynamics
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；North Carolina State University（北卡罗来纳州立大学）；Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院）；Tencent AI Lab（腾讯AI实验室）
McGill University（麦吉尔大学）；Université de Montréal（蒙特利尔大学）；HEC Montréal（蒙特利尔高等商学院）；Mila（米拉人工智能研究所）
Graph Neural Networks (GNNs) are attracting growing attention due to their effectiveness and flexibility in modeling a variety of graph-structured data. Exiting GNN architectures usually adopt simple pooling operations (eg. sum, average, max) when aggregating messages from a local neighborhood for updating node representation or pooling node representations from the entire graph to compute the graph representation. Though simple and effective, these linear operations do not model high-order non-linear interactions among nodes. We propose the Tensorized Graph Neural Network (tGNN), a highly exp…
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Paradigm. Inc.（第四范式）；Department of Electronic Engineering, Tsinghua University（清华大学电子工程系）；Lenovo（联想）
Graph classification is an important problem with applications across many domains, like chemistry and bioinformatics, for which graph neural networks (GNNs) have been state-of-the-art (SOTA) methods. GNNs are designed to learn node-level representation based on neighborhood aggregation schemes, and to obtain graph-level representation, pooling methods are applied after the aggregation operation in existing GNN models to generate coarse-grained graphs. However,due to highly diverse applications of graph classification, and the performance of existing pooling methods vary on different graphs. I…
Graph-level representation learning is the pivotal step for downstream tasks that operate on the whole graph. The most common approach to this problem heretofore is graph pooling, where node features are typically averaged or summed to obtain the graph representations. However, pooling operations like averaging or summing inevitably cause massive information missing, which may severely downgrade the final performance. In this paper, we argue what is crucial to graph-level downstream tasks includes not only the topological structure but also the distribution from which nodes are sampled. Theref…
University of Chinese Academy of Sciences（中国科学院大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Graph convolutional networks (GCNs) have been successfully applied in node classification tasks of network mining. However, most of these models based on neighborhood aggregation are usually shallow and lack the "graph pooling" mechanism, which prevents the model from obtaining adequate global information. In order to increase the receptive field, we propose a novel deep Hierarchical Graph Convolutional Network (H-GCN) for semi-supervised node classification. H-GCN first repeatedly aggregates structurally similar nodes to hyper-nodes and then refines the coarsened graph to the original to rest…
Heriot-Watt University（赫瑞瓦特大学）；University of Oxford（牛津大学）
We study the problem of recovering an underlying 3D shape from a set of images. Existing learning based approaches usually resort to recurrent neural nets, e.g., GRU, or intuitive pooling operations, e.g., max/mean poolings, to fuse multiple deep features encoded from input images. However, GRU based approaches are unable to consistently estimate 3D shapes given different permutations of the same set of input images as the recurrent unit is permutation variant. It is also unlikely to refine the 3D shape given more images due to the long-term memory loss of GRU. Commonly used pooling approaches…
Feature learning on point clouds has shown great promise, with the introduction of effective and generalizable deep learning frameworks such as pointnet++. Thus far, however, point features have been abstracted in an independent and isolated manner, ignoring the relative layout of neighboring points as well as their features. In the present article, we propose to overcome this limitation by using spectral graph convolution on a local graph, combined with a novel graph pooling strategy. In our approach, graph convolution is carried out on a nearest neighbor graph constructed from a point's neig…
Arizona State University（亚利桑那州立大学）；HRL Laboratories, LLC（HRL实验室有限责任公司）
Graph data widely exist in many high-impact applications. Inspired by the success of deep learning in grid-structured data, graph neural network models have been proposed to learn powerful node-level or graph-level representation. However, most of the existing graph neural networks suffer from the following limitations: (1) there is limited analysis regarding the graph convolution properties, such as seed-oriented, degree-aware and order-free; (2) the node's degree-specific graph structure is not explicitly expressed in graph convolution for distinguishing structure-aware node neighborhoods; (…
Attention Beyond Neighborhoods: Reviving Transformer for Graph Clustering
School of Computer Science and Engineering, University of Electronic Science and Technology of China（电子科技大学计算机科学与工程学院）；Michigan State University（密歇根州立大学）；Alibaba Group（阿里巴巴集团）
Can GNNs Learn Link Heuristics? A Concise Review and Evaluation of Link Prediction Methods
Faculty of Engineering and Information Technology, University of Technology Sydney（工程与信息技术学院，悉尼大学）；Faculty of Engineering and Information Sciences, University of Wollongong（工程与信息科学学院，沃林戈大学）；College of Electrical Engineering, Zhejiang University（电气工程学院，浙江大学）
Ludwig Maximilian University of Munich（慕尼黑大学）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心（MCML））；CISPA Helmholtz Center for Information Security（CISPA亥姆霍兹信息安全中心）；Technical University of Munich（慕尼黑工业大学）；University of Tromsø（特罗姆瑟大学）；Technion – Israel Institute of Technology（以色列理工学院）
A powerful framework for studying graphs is to consider them as geometric graphs: nodes are randomly sampled from an underlying metric space, and any pair of nodes is connected if their distance is less than a specified neighborhood radius. Currently, the literature mostly focuses on uniform sampling and constant neighborhood radius. However, real-world graphs are likely to be better represented by a model in which the sampling density and the neighborhood radius can both vary over the latent space. For instance, in a social network communities can be modeled as densely sampled areas, and hubs…
Seoul National University（首尔国立大学）；Adobe Research（奥多比研究院）
In this study, we propose a novel graph neural network called propagate-selector (PS), which propagates information over sentences to understand information that cannot be inferred when considering sentences in isolation. First, we design a graph structure in which each node represents an individual sentence, and some pairs of nodes are selectively connected based on the text structure. Then, we develop an iterative attentive aggregation and a skip-combine method in which a node interacts with its neighborhood nodes to accumulate the necessary information. To evaluate the performance of the pr…
Learning Local Heterogeneity and Cross-Region Context for Large-Scale Traffic Forecasting
Northwestern Polytechnical University（西北工业大学）；City University of Hong Kong（香港城市大学）；Shenzhen Research Institute, City University of Hong Kong（香港城市大学深圳研究院）；Northwest University（西北大学）
