HyperSoRec: Exploiting Hyperbolic User and Item Representations with Multiple Aspects for Social-aware Recommendation

2022 ◽  
Vol 40 (2) ◽  
pp. 1-28
Author(s):  
Hao Wang ◽  
Defu Lian ◽  
Hanghang Tong ◽  
Qi Liu ◽  
Zhenya Huang ◽  
...  
Keyword(s):  
Hyperbolic Space ◽  
Message Passing ◽  
Metric Learning ◽  
Great Success ◽  
Social Recommendation ◽  
Item Pair ◽  
Trade Offs ◽  
Location Based Social Networks ◽  
Public Datasets ◽  
Multiple Aspect

Social recommendation has achieved great success in many domains including e-commerce and location-based social networks. Existing methods usually explore the user-item interactions or user-user connections to predict users’ preference behaviors. However, they usually learn both user and item representations in Euclidean space, which has large limitations for exploring the latent hierarchical property in the data. In this article, we study a novel problem of hyperbolic social recommendation, where we aim to learn the compact but strong representations for both users and items. Meanwhile, this work also addresses two critical domain-issues, which are under-explored. First, users often make trade-offs with multiple underlying aspect factors to make decisions during their interactions with items. Second, users generally build connections with others in terms of different aspects, which produces different influences with aspects in social network. To this end, we propose a novel graph neural network (GNN) framework with multiple aspect learning, namely, HyperSoRec. Specifically, we first embed all users, items, and aspects into hyperbolic space with superior representations to ensure their hierarchical properties. Then, we adapt a GNN with novel multi-aspect message-passing-receiving mechanism to capture different influences among users. Next, to characterize the multi-aspect interactions of users on items, we propose an adaptive hyperbolic metric learning method by introducing learnable interactive relations among different aspects. Finally, we utilize the hyperbolic translational distance to measure the plausibility in each user-item pair for recommendation. Experimental results on two public datasets clearly demonstrate that our HyperSoRec not only achieves significant improvement for recommendation performance but also shows better representation ability in hyperbolic space with strong robustness and reliability.

scholarly journals A Social Recommendation Based on Metric Learning and Users’ Co-Occurrence Pattern

Symmetry ◽  
2021 ◽  
Vol 13 (11) ◽  
pp. 2158
Author(s):  
Xin Zhang ◽  
Jiwei Qin ◽  
Jiong Zheng
Keyword(s):  
Matrix Factorization ◽  
Triangle Inequality ◽  
Metric Learning ◽  
Social Recommendation ◽  
Rating Data ◽  
Fine Grained ◽  
Information Metric ◽  
Occurrence Pattern ◽  
Public Datasets ◽  
Occurrence Patterns

For personalized recommender systems, matrix factorization and its variants have become mainstream in collaborative filtering. However, the dot product in matrix factorization does not satisfy the triangle inequality and therefore fails to capture fine-grained information. Metric learning-based models have been shown to be better at capturing fine-grained information than matrix factorization. Nevertheless, most of these models only focus on rating data and social information, which are not sufficient for dealing with the challenges of data sparsity. In this paper, we propose a metric learning-based social recommendation model called SRMC. SRMC exploits users’ co-occurrence patterns to discover their potentially similar or dissimilar users with symmetric relationships and change their relative positions to achieve better recommendations. Experiments on three public datasets show that our model is more effective than the compared models.

scholarly journals A Social Recommendation Based on Metric Learning and Users’ Co-occurrence Pattern

2021 ◽  
Author(s):  
Xin Zhang ◽  
Jiwei Qin ◽  
Jiong Zheng
Keyword(s):  
Recommender Systems ◽  
Matrix Factorization ◽  
Triangle Inequality ◽  
Metric Learning ◽  
Social Recommendation ◽  
Rating Data ◽  
Fine Grained ◽  
Information Metric ◽  
Occurrence Pattern ◽  
Public Datasets

For personalized recommender systems,matrix factorization and its variants have become mainstream in collaborative filtering.However,the dot product in matrix factorization does not satisfy the triangle inequality and therefore fails to capture fine-grained information. Metric learning-based models have been shown to be better at capturing fine-grained information than matrix factorization. Nevertheless,most of these models only focus on rating data and social information, which are not sufficient for dealing with the challenges of data sparsity. In this paper,we propose a metric learning-based social recommendation model called SRMC.SRMC exploits users' co-occurrence pattern to discover their potentially similar or dissimilar users with symmetric relationships and change their relative positions to achieve better recommendations.Experiments on three public datasets show that our model is more effective than the compared models.

scholarly journals An improved boundary-aware face alignment using stacked dense U-Nets

2020 ◽  
Vol 17 (4) ◽  
pp. 172988142094090
Author(s):  
Jianghao Ye ◽  
Ying Cui ◽  
Xiang Pan ◽  
Herong Zheng ◽  
Dongyan Guo ◽  
...  
Keyword(s):  
Message Passing ◽  
Face Alignment ◽  
Shape Variation ◽  
Facial Landmark Localization ◽  
Facial Landmark ◽  
Public Datasets ◽  
Pose Variation ◽  
Two Stages ◽  
Landmark Localization ◽  
Boundary Lines

Facial landmark localization is still a challenge task in the unconstrained environment with influences of significant variation conditions such as facial pose, shape, expression, illumination, and occlusions. In this work, we present an improved boundary-aware face alignment method by using stacked dense U-Nets. The proposed method consists of two stages: a boundary heatmap estimation stage to learn the facial boundary lines and a facial landmark localization stage to predict the final face alignment result. With the constraint of boundary lines, facial landmarks are unified as a whole facial shape. Hence, the unseen landmarks in a shape with occlusions can be better estimated by message passing with other landmarks. By introducing the stacked dense U-Nets for feature extraction, the capacity of the model is improved. Experiments and comparisons on public datasets show that the proposed method obtains better performance than the baselines, especially for facial images with large pose variation, shape variation, and occlusions.

scholarly journals Context-Aware POI Sequence Recommendation with Attention-Based Neural Network

2019 ◽  
Vol 1 ◽  
pp. 1-2
Author(s):  
Jianfeng Huang ◽  
Yuefeng Liu ◽  
Yue Chen ◽  
Chen Jia
Keyword(s):  
Neural Network ◽  
Network Models ◽  
Learning Ability ◽  
Great Success ◽  
Context Aware ◽  
Neural Network Models ◽  
Powerful Learning ◽  
The Neural Network ◽  
Poi Recommendation ◽  
Location Based Social Networks

<p><strong>Abstract.</strong> Location-based social networks (LBSNs) is playing an increasingly important role in our daily life, through which users can share their locations and location-related contents at any time. The Location information implicitly expresses user's behaviour preference. Therefore, LBSNs is being widely explored for Point-of-Interest (POI) recommendation in recent years. Most of existing POI recommenders only recommend a single POI, while sometimes successive POI sequence recommendation is more practical. For example, when we travel to a strange city, what we expect is not a single POI recommendation, but a POI sequence recommendation which contains a set of POIs and the order of visiting them. To solve this problem, this paper proposes a novel model called Context-Aware POI Sequence Recommendation (CPSR), which is developed based on an attention-based neural network. Neural network has made a great success in various of field because of its powerful learning ability. Recently, dozens of works has demonstrated that attention mechanism can make the neural network models more reasonable.</p>

scholarly journals Triplet Enhanced AutoEncoder: Model-free Discriminative Network Embedding

2019 ◽  
Author(s):  
Yao Yang ◽  
Haoran Chen ◽  
Junming Shao
Keyword(s):  
Metric Learning ◽  
Expressive Power ◽  
Network Embedding ◽  
Model Free ◽  
The Neural Network ◽  
Latent Space ◽  
Label Information ◽  
Triplet Loss ◽  
Low Dimensional ◽  
Public Datasets

Deep autoencoder is widely used in dimensionality reduction because of the expressive power of the neural network. Therefore, it is naturally suitable for embedding tasks, which essentially compresses high-dimensional information into a low-dimensional latent space. In terms of network representation, methods based on autoencoder such as SDNE and DNGR have achieved comparable results with the state-of-arts. However, all of them do not leverage label information, which leads to the embeddings lack the characteristic of discrimination. In this paper, we present Triplet Enhanced AutoEncoder (TEA), a new deep network embedding approach from the perspective of metric learning. Equipped with the triplet-loss constraint, the proposed approach not only allows capturing the topological structure but also preserving the discriminative information. Moreover, unlike existing discriminative embedding techniques, TEA is independent of any specific classifier, we call it the model-free property. Extensive empirical results on three public datasets (i.e, Cora, Citeseer and BlogCatalog) show that TEA is stable and achieves state-of-the-art performance compared with both supervised and unsupervised network embedding approaches on various percentages of labeled data. The source code can be obtained from https://github.com/yybeta/TEA.

On the role of shared entanglement

2008 ◽  
Vol 8 (1&2) ◽  
pp. 82-95
Author(s):  
D. Gavinsky
Keyword(s):  
Lower Bounds ◽  
Message Passing ◽  
Communication Complexity ◽  
Optimal Solution ◽  
Famous Theorem ◽  
Trade Offs ◽  
Wide Range ◽  
Bounded Error ◽  
Strong Direct Product Theorem ◽  
Apparent Similarity

Despite the apparent similarity between shared randomness and shared entanglement in the context of Communication Complexity, our understanding of the latter is not as good as of the former. In particular, there is no known ``entanglement analogue'' for the famous theorem by Newman, saying that the number of shared random bits required for solving any communication problem can be at most logarithmic in the input length (i.e., using more than $\asO[]{\log n}$ shared random bits would not reduce the complexity of an optimal solution). In this paper we prove that the same is not true for entanglement. We establish a wide range of tight (up to a polylogarithmic factor) entanglement vs.\ communication trade-offs for relational problems. The low end is:\ for any $t>2$, reducing shared entanglement from $log^tn$ to $\aso[]{log^{t-2}n}$ qubits can increase the communication required for solving a problem almost exponentially, from $\asO[]{log^tn}$ to $\asOm[]{\sqrt n}$. The high end is:\ for any $\eps>0$, reducing shared entanglement from $n^{1-\eps}\log n$ to $\aso[]{n^{1-\eps}/\log n}$ can increase the required communication from $\asO[]{n^{1-\eps}\log n}$ to $\asOm[]{n^{1-\eps/2}/\log n}$. The upper bounds are demonstrated via protocols which are \e{exact} and work in the \e{simultaneous message passing model}, while the lower bounds hold for \e{bounded-error protocols}, even in the more powerful \e{model of 1-way communication}. Our protocols use shared EPR pairs while the lower bounds apply to any sort of prior entanglement. We base the lower bounds on a strong direct product theorem for communication complexity of a certain class of relational problems. We believe that the theorem might have applications outside the scope of this work.

FEATURE FUSION AND MODEL SELECTION BASED ON INFORMATION CRITERION

2006 ◽  
Vol 03 (02) ◽  
pp. 85-99
Author(s):  
TAKAMI SATONAKA ◽  
KEIICHI UCHIMURA
Keyword(s):  
Variance Estimation ◽  
Feature Fusion ◽  
Likelihood Function ◽  
Asymptotic Variance ◽  
Metric Learning ◽  
Information Criterion ◽  
Trade Offs ◽  
Training Samples ◽  
Fusion Methods ◽  
The Face

We describe the k-NN adaptive metric learning procedure combining the asymptotic variance estimation and fine adjustment of the metric parameters for the face recognition. The metric learning model based on the Mahalanobis distance suffered from the degraded performance due to the limitation of available training samples. The feature fusion methods are proposed to assume local distributions of feature patterns for the parameter estimation and learning. Firstly, the MDL criterion is formulated to decide on the trade-offs between accuracy and complexity of an asymptotic statistical model. The variance within the classes is minimized by using the asymptotic variance estimation. Secondly, optimal metric parameters are derived from the minimization of the negative log-likelihood function for the presentation of the synthesized feature patterns. The variance between the classes is increased by using the simulated annealing method. We present the simulation results using the ORL and UMIST databases.

scholarly journals Performance evaluation and analysis of distributed multi-agent optimization algorithms with sparsified directed communication

2021 ◽  
Vol 2021 (1) ◽  
Author(s):  
Lidija Fodor ◽  
Dušan Jakovetić ◽  
Nataša Krejić ◽  
Nataša Krklec Jerinkić ◽  
Srđan Škrbić
Keyword(s):  
Message Passing ◽  
High Performance ◽  
Message Passing Interface ◽  
Small Body ◽  
Optimization Algorithms ◽  
Empirical Evaluation ◽  
Big Data Analytics ◽  
Linear Convergence ◽  
Programming Environments ◽  
Trade Offs

AbstractThere has been significant interest in distributed optimization algorithms, motivated by applications in Big Data analytics, smart grid, vehicle networks, etc. While there have been extensive theory and theoretical advances, a proportionally small body of scientific literature focuses on numerical evaluation of the proposed methods in actual practical, parallel programming environments. This paper considers a general algorithmic framework of first and second order methods with sparsified communications and computations across worker nodes. The considered framework subsumes several existing methods. In addition, a novel method that utilizes unidirectional sparsified communications is introduced and theoretical convergence analysis is also provided. Namely, we prove R-linear convergence in the expected norm. A thorough empirical evaluation of the methods using Message Passing Interface (MPI) on a High Performance Computing (HPC) cluster is carried out and several useful insights and guidelines on the performance of algorithms and inherent communication-computational trade-offs in a realistic setting are derived.

Sign in / Sign up

Export Citation Format

Share Document