Variational Bayesian representation learning for grocery recommendation

AbstractRepresentation learning has been widely applied in real-world recommendation systems to capture the features of both users and items. Existing grocery recommendation methods only represent each user and item by single deterministic points in a low-dimensional continuous space, which limit the expressive ability of their embeddings, resulting in recommendation performance bottlenecks. In addition, existing representation learning methods for grocery recommendation only consider the items (products) as independent entities, neglecting their other valuable side information, such as the textual descriptions and the categorical data of items. In this paper, we propose the Variational Bayesian Context-Aware Representation (VBCAR) model for grocery recommendation. VBCAR is a novel variational Bayesian model that learns distributional representations of users and items by leveraging basket context information from historical interactions. Our VBCAR model is also extendable to leverage side information by encoding contextual features into representations based on the inference encoder. We conduct extensive experiments on three real-world grocery datasets to assess the effectiveness of our model as well as the impact of different construction strategies for item side information. Our results show that our VBCAR model outperforms the current state-of-the-art grocery recommendation models while integrating item side information (especially the categorical features with the textual information of items) results in further significant performance gains. Furthermore, we demonstrate through analysis that our model is able to effectively encode similarities between product types, which we argue is the primary reason for the observed effectiveness gains.

Download Full-text

Negative Sampling in Knowledge Representation Learning: A Mini-Review

10.5121/csit.2020.101519 ◽

2020 ◽

Author(s):

Jing Qian ◽

Gangmin Li ◽

Katie Atkinson ◽

Yong Yue

Keyword(s):

Knowledge Representation ◽

Link Prediction ◽

Representation Learning ◽

Cluster Sampling ◽

Continuous Space ◽

Knowledge Representations ◽

Space Efficiency ◽

Low Dimensional ◽

Fixed Distribution

Knowledge representation learning (KRL) aims at encoding components of a knowledge graph (KG) into a low-dimensional continuous space, which has brought considerable successes in applying deep learning to graph embedding. Most famous KGs contain only positive instances for space efficiency. Typical KRL techniques, especially translational distance-based models, are trained through discriminating positive and negative samples. Thus, negative sampling is unquestionably a non-trivial step in KG embedding. The quality of generated negative samples can directly influence the performance of final knowledge representations in downstream tasks, such as link prediction and triple classification. This review summarizes current negative sampling methods in KRL and we categorize them into three sorts, fixed distribution-based, generative adversarial net (GAN)-based and cluster sampling. Based on this categorization we discuss the most prevalent existing approaches and their characteristics.

Download Full-text

LkeRec: Toward Lightweight End-to-End Joint Representation Learning for Building Accurate and Effective Recommendation

ACM Transactions on Information Systems ◽

10.1145/3486673 ◽

2022 ◽

Vol 40 (3) ◽

pp. 1-28

Author(s):

Surong Yan ◽

Kwei-Jay Lin ◽

Xiaolin Zheng ◽

Haosen Wang

Keyword(s):

Side Information ◽

Dimensional Space ◽

Representation Learning ◽

Knowledge Graph ◽

Learning Framework ◽

Relation Type ◽

End To End ◽

Low Dimensional ◽

Item Knowledge ◽

Explicit And Implicit Knowledge

Explicit and implicit knowledge about users and items have been used to describe complex and heterogeneous side information for recommender systems (RSs). Many existing methods use knowledge graph embedding (KGE) to learn the representation of a user-item knowledge graph (KG) in low-dimensional space. In this article, we propose a lightweight end-to-end joint learning framework for fusing the tasks of KGE and RSs at the model level. Our method proposes a lightweight KG embedding method by using bidirectional bijection relation-type modeling to enable scalability for large graphs while using self-adaptive negative sampling to optimize negative sample generating. Our method further generates the integrated views for users and items based on relation-types to explicitly model users’ preferences and items’ features, respectively. Finally, we add virtual “recommendation” relations between the integrated views of users and items to model the preferences of users on items, seamlessly integrating RS with user-item KG over a unified graph. Experimental results on multiple datasets and benchmarks show that our method can achieve a better accuracy of recommendation compared with existing state-of-the-art methods. Complexity and runtime analysis suggests that our method can gain a lower time and space complexity than most of existing methods and improve scalability.

Download Full-text

Benefits of Technology Adoption for Enhanced Integration of Port–Hinterland Operations

Transportation Research Record Journal of the Transportation Research Board ◽

10.1177/0361198120949251 ◽

2020 ◽

Vol 2674 (11) ◽

pp. 606-615

Author(s):

Agustina Calatayud ◽

Mario Monsreal ◽

John Mangan ◽

Juan Villa

Keyword(s):

Supply Chain ◽

Real Data ◽

Positioning Systems ◽

Ict Adoption ◽

Information And Communication ◽

Significant Performance ◽

Important Means ◽

Time Utilization ◽

Performance Gains ◽

The Impact

Because container shipping is the most important means of transportation for international trade, the integration of port–hinterland operations is critical to improve the performance of global supply chains. Information and communication technology (ICT) can assist port stakeholders in addressing bottlenecks and streamlining processes at the port–hinterland interface. However, ICT adoption is often hindered by uncertainties concerning expected gains. This paper shows that the adoption of well-established technologies for supply chain management—namely barcode and global positioning systems technology—can bring significant performance gains for the port–hinterland interface, as evidenced by increased container cycle time, utilization rates, and total throughput. In addition, results show the presence of diminishing returns when implementing multiple readers in the system. System dynamics and a unique database containing real data from the Hutchinson Terminal at the Port of Veracruz, Mexico—selected because it is one of the most important ports in the Americas—are used to show the benefits that both local (nodes) and global (supply chain) levels can obtain from ICT adoption. The results of this research will help to reduce uncertainty and incentivize ICT adoption by port stakeholders, particularly in developing countries where research is lagging. The model proposed here can be applied to any port to analyze the impact of ICT adoption and provide support for the decision making of port stakeholders.

Download Full-text

The impact of ischemic stroke on connectivity gradients

10.1101/481689 ◽

2018 ◽

Cited By ~ 1

Author(s):

Şeyma Bayrak ◽

Ahmed A. Khalil ◽

Kersten Villringer ◽

Jochen B. Fiebach ◽

Arno Villringer ◽

...

Keyword(s):

Functional Connectivity ◽

Three Dimensional ◽

Connectivity Matrix ◽

Continuous Space ◽

Functional Deficits ◽

Stroke Research ◽

Low Dimensional ◽

The Impact ◽

The Relationship ◽

The Brain

AbstractUnderstanding the relationship between localized anatomical damage, reorganization, and functional deficits is a major challenge in stroke research. Previous work has shown that localized lesions cause widespread functional connectivity alterations in structurally intact areas, thereby affecting a whole network of interconnected regions. Recent advances suggest an alternative to discrete functional networks by describing a connectivity space based on a low-dimensional embedding of the full connectivity matrix. The dimensions of this space, described as connectivity gradients, capture the similarity of areas’ connections along a continuous space. Here, we defined a three-dimensional connectivity space template based on functional connectivity data from healthy controls. By projecting lesion locations into this space, we demonstrate that ischemic strokes resulted in dimension-specific alterations in functional connectivity over the first week after symptoms onset. Specifically, changes in functional connectivity were captured along connectivity Gradients 1 and 3. The degree of change in functional connectivity was determined by the distance from the lesion along these connectivity gradients regardless of the anatomical distance from the lesion. Together, these results provide a novel framework to study reorganization after stroke and suggest that, rather than only impacting on anatomically proximate areas, the indirect effects of ischemic strokes spread along the brain relative to the space defined by its connectivity.

Download Full-text

TextGTL: Graph-based Transductive Learning for Semi-supervised Text Classification via Structure-Sensitive Interpolation

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2021/369 ◽

2021 ◽

Author(s):

Chen Li ◽

Xutan Peng ◽

Hao Peng ◽

Jianxin Li ◽

Lihong Wang

Keyword(s):

Text Classification ◽

Data Augmentation ◽

Oriented Graph ◽

Representation Learning ◽

Free Text ◽

Transductive Learning ◽

Benchmark Datasets ◽

Significant Performance ◽

Performance Gains ◽

Global And Local

Compared with traditional sequential learning models, graph-based neural networks exhibit excellent properties when encoding text, such as the capacity of capturing global and local information simultaneously. Especially in the semi-supervised scenario, propagating information along the edge can effectively alleviate the sparsity of labeled data. In this paper, beyond the existing architecture of heterogeneous word-document graphs, for the first time, we investigate how to construct lightweight non-heterogeneous graphs based on different linguistic information to better serve free text representation learning. Then, a novel semi-supervised framework for text classification that refines graph topology under theoretical guidance and shares information across different text graphs, namely Text-oriented Graph-based Transductive Learning (TextGTL), is proposed. TextGTL also performs attribute space interpolation based on dense substructure in graphs to predict low-entropy labels with high-quality feature nodes for data augmentation. To verify the effectiveness of TextGTL, we conduct extensive experiments on various benchmark datasets, observing significant performance gains over conventional heterogeneous graphs. In addition, we also design ablation studies to dive deep into the validity of components in TextTGL.

Download Full-text

Context Attention Heterogeneous Network Embedding

Computational Intelligence and Neuroscience ◽

10.1155/2019/8106073 ◽

2019 ◽

Vol 2019 ◽

pp. 1-15

Author(s):

Wei Zhuo ◽

Qianyi Zhan ◽

Yuan Liu ◽

Zhenping Xie ◽

Jing Lu

Keyword(s):

Real World ◽

Online Social Networks ◽

Heterogeneous Network ◽

Network Embedding ◽

Node Importance ◽

Unweighted Network ◽

Real World Datasets ◽

Low Dimensional ◽

Types Of Information ◽

The Impact

Network embedding (NE), which maps nodes into a low-dimensional latent Euclidean space to represent effective features of each node in the network, has obtained considerable attention in recent years. Many popular NE methods, such as DeepWalk, Node2vec, and LINE, are capable of handling homogeneous networks. However, nodes are always fully accompanied by heterogeneous information (e.g., text descriptions, node properties, and hashtags) in the real-world network, which remains a great challenge to jointly project the topological structure and different types of information into the fixed-dimensional embedding space due to heterogeneity. Besides, in the unweighted network, how to quantify the strength of edges (tightness of connections between nodes) accurately is also a difficulty faced by existing methods. To bridge the gap, in this paper, we propose CAHNE (context attention heterogeneous network embedding), a novel network embedding method, to accurately determine the learning result. Specifically, we propose the concept of node importance to measure the strength of edges, which can better preserve the context relations of a node in unweighted networks. Moreover, text information is a widely ubiquitous feature in real-world networks, e.g., online social networks and citation networks. On account of the sophisticated interactions between the network structure and text features of nodes, CAHNE learns context embeddings for nodes by introducing the context node sequence, and the attention mechanism is also integrated into our model to better reflect the impact of context nodes on the current node. To corroborate the efficacy of CAHNE, we apply our method and various baseline methods on several real-world datasets. The experimental results show that CAHNE achieves higher quality compared to a number of state-of-the-art network embedding methods on the tasks of network reconstruction, link prediction, node classification, and visualization.

Download Full-text

Decorrelated Clustering with Data Selection Bias

Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2020/301 ◽

2020 ◽

Author(s):

Xiao Wang ◽

Shaohua Fan ◽

Kun Kuang ◽

Chuan Shi ◽

Jiawei Liu ◽

...

Keyword(s):

Selection Bias ◽

Real World ◽

Clustering Algorithms ◽

Data Distribution ◽

Data Selection ◽

Sample Distribution ◽

Sample Weights ◽

Significant Performance ◽

Real World Datasets ◽

Performance Gains

Most of existing clustering algorithms are proposed without considering the selection bias in data. In many real applications, however, one cannot guarantee the data is unbiased. Selection bias might bring the unexpected correlation between features and ignoring those unexpected correlations will hurt the performance of clustering algorithms. Therefore, how to remove those unexpected correlations induced by selection bias is extremely important yet largely unexplored for clustering. In this paper, we propose a novel Decorrelation regularized K-Means algorithm (DCKM) for clustering with data selection bias. Specifically, the decorrelation regularizer aims to learn the global sample weights which are capable of balancing the sample distribution, so as to remove unexpected correlations among features. Meanwhile, the learned weights are combined with k-means, which makes the reweighted k-means cluster on the inherent data distribution without unexpected correlation influence. Moreover, we derive the updating rules to effectively infer the parameters in DCKM. Extensive experiments results on real world datasets well demonstrate that our DCKM algorithm achieves significant performance gains, indicating the necessity of removing unexpected feature correlations induced by selection bias when clustering.

Download Full-text

MEGAN: A Generative Adversarial Network for Multi-View Network Embedding

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2019/489 ◽

2019 ◽

Cited By ~ 6

Author(s):

Yiwei Sun ◽

Suhang Wang ◽

Tsung-Yu Hsieh ◽

Xianfeng Tang ◽

Vasant Honavar

Keyword(s):

Real World ◽

Representation Learning ◽

Data Sets ◽

Network Embedding ◽

Generative Adversarial Network ◽

Single View ◽

Adversarial Network ◽

Different Types ◽

The Individual ◽

Low Dimensional

Data from many real-world applications can be naturally represented by multi-view networks where the different views encode different types of relationships (e.g., friendship, shared interests in music, etc.) between real-world individuals or entities. There is an urgent need for methods to obtain low-dimensional, information preserving and typically nonlinear embeddings of such multi-view networks. However, most of the work on multi-view learning focuses on data that lack a network structure, and most of the work on network embeddings has focused primarily on single-view networks. Against this background, we consider the multi-view network representation learning problem, i.e., the problem of constructing low-dimensional information preserving embeddings of multi-view networks. Specifically, we investigate a novel Generative Adversarial Network (GAN) framework for Multi-View Network Embedding, namely MEGAN, aimed at preserving the information from the individual network views, while accounting for connectivity across (and hence complementarity of and correlations between) different views. The results of our experiments on two real-world multi-view data sets show that the embeddings obtained using MEGAN outperform the state-of-the-art methods on node classification, link prediction and visualization tasks.

Download Full-text

CuCo: Graph Representation with Curriculum Contrastive Learning

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2021/317 ◽

2021 ◽

Author(s):

Guanyi Chu ◽

Xiao Wang ◽

Chuan Shi ◽

Xunqiang Jiang

Keyword(s):

Real World ◽

Scoring Function ◽

Representation Learning ◽

Parameter Analysis ◽

Graph Representation ◽

Training Procedure ◽

Graph Classification ◽

Graph Augmentation ◽

Real World Datasets ◽

The Impact

Graph-level representation learning is to learn low-dimensional representation for the entire graph, which has shown a large impact on real-world applications. Recently, limited by expensive labeled data, contrastive learning based graph-level representation learning attracts considerable attention. However, these methods mainly focus on graph augmentation for positive samples, while the effect of negative samples is less explored. In this paper, we study the impact of negative samples on learning graph-level representations, and a novel curriculum contrastive learning framework for self-supervised graph-level representation, called CuCo, is proposed. Specifically, we introduce four graph augmentation techniques to obtain the positive and negative samples, and utilize graph neural networks to learn their representations. Then a scoring function is proposed to sort negative samples from easy to hard and a pacing function is to automatically select the negative samples in each training procedure. Extensive experiments on fifteen graph classification real-world datasets, as well as the parameter analysis, well demonstrate that our proposed CuCo yields truly encouraging results in terms of performance on classification and convergence.

Download Full-text