CAD assembly modeling, which refers to using CAD software to design new products from a catalog of existing machine components, is important in the industrial field. The graph neural network (GNN) based recommender system for CAD assembly modeling can help designers make decisions and speed up the design process by recommending the next required component based on the existing components in CAD software. These components can be represented as a graph naturally. However, present recommender systems for CAD assembly modeling adopt fixed GNN architectures, which may be sub-optimal for different manufacturers with different data distribution. Therefore, to customize a well-suited recommender system for different manufacturers, we propose a novel neural architecture search (NAS) framework, dubbed CusGNN, which can design data-specific GNN automatically. Specifically, we design a search space from three dimensions (i.e., aggregation, fusion, and readout functions), which contains a wide variety of GNN architectures. Then, we develop an effective differentiable search algorithm to search high-performing GNN from the search space. Experimental results show that the customized GNNs achieve 1.5-5.1% higher top-10 accuracy compared to previous manual designed methods, demonstrating the superiority of the proposed approach. Code and data are available at https://github.com/BUPT-GAMMA/CusGNN.

Graph classification is an important problem with applications across many domains, for which graph neural networks (GNNs) have been state-of-the-art (SOTA) methods. In the literature, to adopt GNNs for the graph classification task, there are two groups of methods: global pooling and hierarchical pooling. The global pooling methods obtain the graph representation vectors by globally pooling all of the node embeddings together at the end of several GNN layers, whereas the hierarchical pooling methods provide one extra pooling operation between the GNN layers to extract hierarchical information and improve the graph representations. Both global and hierarchical pooling methods are effective in different scenarios. Due to highly diverse applications, it is challenging to design data-specific pooling methods with human expertise. To address this problem, we propose PAS (Pooling Architecture Search) to design adaptive pooling architectures by using the neural architecture search (NAS). To enable the search space design, we propose a unified pooling framework consisting of four modules: Aggregation, Pooling, Readout, and Merge. Two variants, PAS-G and PAS-NE, are provided to design the pooling operations in different scales. A set of candidate operations is designed in the search space using this framework. Then, existing human-designed pooling methods, including global and hierarchical ones, can be incorporated. To enable efficient search, a coarsening strategy is developed to continuously relax the search space, and then a differentiable search method can be adopted. We conduct extensive experiments on six real-world datasets, including the large-scale datasets MR and ogbg-molhiv. Experimental results in this article demonstrate the effectiveness and efficiency of the proposed PAS in designing the pooling architectures for graph classification. The Top-1 performance on two Open Graph Benchmark (OGB) datasets 1 further indicates the utility of PAS when facing diverse realistic data. The implementation of PAS is available at: https://github.com/AutoML-Research/PAS.

Graph Neural Networks (GNNs) have been widely used in Collaborative Filtering (CF). However, when given a new recommendation scenario, the current options are either selecting from existing GNN architectures or employing Neural Architecture Search (NAS) to obtain a well-performing GNN model, both of which are expensive in terms of human expertise or computational resources.To address the problem, in this work,we propose a novel neural retrieval approach, dubbed RGCF, to search a well-performing architecture for GNN-based CF rapidly when handling new scenarios. Specifically, we design the neural retrieval approach based on meta-learning by developing two-level meta-features, ranking loss, and task-level data augmentation, and in a retrieval paradigm, RGCF can directly return a well-performing architecture given a new dataset (query), thus being efficient inherently. Experimental results on two mainstream tasks, i.e., rating prediction and item ranking, show that RGCF outperforms all models either by human-designed or NAS on two new datasets in terms of effectiveness and efficiency. Particularly, the efficiency improvement is significant, taking as an example that RGCF is 61.7-206.3x faster than a typical reinforcement learning based NAS approach on the two new datasets. Code and data are available at https://github.com/BUPT-GAMMA/RGCF.

In recent years, Heterogeneous Graph Neural Networks (HGNNs) have been the state-of-the-art approaches for various tasks on Heterogeneous Graphs (HGs), e.g., recommendation and social network analysis. Despite the success of existing HGNNs, the utilization of the intricate semantic information in HGs is still insufficient. In this work, we study the problem of how to design powerful HGNNs under the guidance of node-dependent semantics. Specifically, to perform semantic search over HGNNs, we propose to develop semantic structures in terms of relation selection and connection selection, which could guide a task-relevant message flow. Furthermore, to better capture the diversified property of different node samples in HGs, we design predictors to adaptively decide the semantic structures per node. Extensive experiments on seven benchmarking datasets across different downstream tasks, i.e., node classification and recommendation, show that our method can consistently outperform various state-of-the-art baselines with shorter inference latency, which justifies its effectiveness and efficiency. The code and data are available at https://github.com/BUPT-GAMMA/NDS.

Molecular property prediction is an important problem in drug discovery and materials science. As geometric structures have been demonstrated necessary for molecular property prediction,3D information has been combined with various graph learning methods to boost prediction performance. However, obtaining the geometric structure of molecules is not feasible in many real-world applications due to the high computational cost. In this work, we propose a novel 3D pre-training framework (dubbed 3D PGT), which pre-trains a model on 3D molecular graphs, and then fine-tunes it on molecular graphs without 3D structures. Based on fact that bond length, bond angle, and dihedral angle are three basic geometric descriptors corresponding to a complete molecular 3D conformer, we first develop a multi-task generative pre-train framework based on these three attributes. Next, to automatically fuse these three generative tasks, we design a surrogate metric using the total energy to search for weight distribution of the three pretext tasks since total energy corresponding to the quality of 3D conformer. Extensive experiments on 2D molecular graphs are conducted to demonstrate the accuracy, efficiency and generalization ability of the proposed 3D PGT compared to various pre-training baselines.

In recent years, Graph Neural Networks (GNNs) have been popular in the graph classification task. Currently, shallow GNNs are more common due to the well-known over-smoothing problem facing deeper GNNs. However, they are sub-optimal without utilizing the information from distant nodes, i.e., the long-range dependencies. The mainstream methods in the graph classification task can extract the long-range dependencies either by designing the pooling operations or incorporating the higher-order neighbors, while they have evident drawbacks by modifying the original graph structure, which may result in information loss in graph structure learning. In this paper, by justifying the smaller influence of the over-smoothing problem in the graph classification task, we evoke the importance of stacking-based GNNs and then employ them to capture the long-range dependencies without modifying the original graph structure. To achieve this, two design needs are given for stacking-based GNNs, i.e., sufficient model depth and adaptive skip-connection schemes. By transforming the two design needs into designing data-specific inter-layer connections, we propose a novel approach with the help of neural architecture search (NAS), which is dubbed LRGNN (Long-Range Graph Neural Networks). Extensive experiments on five datasets show that the proposed LRGNN can achieve the best performance, and obtained data-specific GNNs with different depth and skip-connection schemes, which can better capture the long-range dependencies. 1

Zero-shot cross-lingual event argument extraction (EAE) is a challenging yet practical problem in Information Extraction. Most previous works heavily rely on external structured linguistic features, which are not easily accessible in real-world scenarios. This paper investigates a translation-based method to implicitly project annotations from the source language to the target language. With the use of translation-based parallel corpora, no additional linguistic features are required during training and inference. As a result, the proposed approach is more cost effective than previous works on zero-shot cross-lingual EAE. Moreover, our implicit annotation projection approach introduces less noises and hence is more effective and robust than explicit ones. Experimental results show that our model achieves the best performance, outperforming a number of competitive baselines. The thorough analysis further demonstrates the effectiveness of our model compared to explicit annotation projection approaches.

Heterogeneous Graph Neural Network (HGNN) has been successfully employed in various tasks, but we cannot accurately know the importance of different design dimensions of HGNNs due to diverse architectures and applied scenarios. Besides, in the research community of HGNNs, implementing and evaluating various tasks still need much human effort. To mitigate these issues, we first propose a unified framework covering most HGNNs, consisting of three components: heterogeneous linear transformation, heterogeneous graph transformation, and heterogeneous message passing layer. Then we build a platform Space4HGNN by defining a design space for HGNNs based on the unified framework, which offers modularized components, reproducible implementations, and standardized evaluation for HGNNs. Finally, we conduct experiments to analyze the effect of different designs. With the insights found, we distill a condensed design space and verify its effectiveness.

In recent years, Graph Neural Networks (GNNs) have been widely used in Collaborative Filtering (CF), one of the most popular methods in recommender systems. However, most existing works focus on designing an individual model architecture given a specific scenario, without studying the influences of different design dimensions. Thus, it remains a challenging problem to quickly obtain a top-performing model in a new recommendation scenario. To address the problem, in this work, we make the first attempt to profile the design space of GNN-based CF methods to enrich the understanding of different design dimensions as well as provide a novel paradigm of model design. Specifically, a unified framework of GNN-based CF is proposed, on top of which a design space is developed and evaluated by extensive experiments. Interesting findings on the impacts of different design dimensions on recommendation performance are obtained. Guided by the empirical findings, we further prune the design space to obtain a compact one containing a higher concentration of top-performing models. Empirical studies demonstrate its high quality and strong generalization ability.

In recent years, Graph Neural Networks (GNNs) have shown superior performance on diverse real-world applications. To improve the model capacity, besides designing aggregation operations, GNN topology design is also very important. In general, there are two mainstream GNN topology design manners. The first one is to stack aggregation operations to obtain the higher-level features but easily got performance drop as the network goes deeper. Secondly, the multiple aggregation operations are utilized in each layer which provides adequate and independent feature extraction stage on local neighbors while are costly to obtain the higher-level information. To enjoy the benefits while alleviating the corresponding deficiencies of these two manners, we learn to design the topology of GNNs in a novel feature fusion perspective which is dubbed F2GNN. To be specific, we provide a feature fusion perspective in designing GNN topology and propose a novel framework to unify the existing topology designs with feature selection and fusion strategies. Then we develop a neural architecture search method on top of the unified framework which contains a set of selection and fusion operations in the search space and an improved differentiable search algorithm. The performance gains on diverse datasets, five homophily and three heterophily ones, demonstrate the effectiveness of F2GNN. We further conduct experiments to show that F2GNN can improve the model capacity while alleviating the deficiencies of existing GNN topology design manners, especially alleviating the over-smoothing problem, by utilizing different levels of features adaptively. 1

Various data mining tasks have been proposed to study Community Question Answering (CQA) platforms like Stack Overflow. The relatedness between some of these tasks provides useful learning signals to each other via Multi-Task Learning (MTL). However, due to the high heterogeneity of these tasks, few existing works manage to jointly solve them in a unified framework. To tackle this challenge, we develop a multi-relational graph based MTL model called Heterogeneous Multi-Task Graph Isomorphism Network (HMTGIN) which efficiently solves heterogeneous CQA tasks. In each training forward pass, HMTGIN embeds the input CQA forum graph by an extension of Graph Isomorphism Network and skip connections. The embeddings are then shared across all task-specific output layers to compute respective losses. Moreover, two cross-task constraints based on the domain knowledge about tasks' relationships are used to regularize the joint learning. In the evaluation, the embeddings are shared among different task-specific output layers to make corresponding predictions. To the best of our knowledge, HMTGIN is the first MTL model capable of tackling CQA tasks from the aspect of multi-relational graphs. To evaluate HMTGIN's effectiveness, we build a novel large-scale multi-relational graph CQA dataset with over two million nodes from Stack Overflow. Extensive experiments show that: (1) HMTGIN is superior to all baselines on five tasks; (2) The proposed MTL strategy and cross-task constraints have substantial advantages.

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. In other words, it is a challenging problem to design a universal pooling architecture to perform well in most cases, leading to a demand for data-specific pooling methods in real-world applications. To address this problem, we propose to use neural architecture search (NAS) to search for adaptive pooling architectures for graph classification. Firstly we designed a unified framework consisting of four modules: Aggregation, Pooling, Readout, and Merge, which can cover existing human-designed pooling methods for graph classification. Based on this framework, a novel search space is designed by incorporating popular operations in human-designed architectures. Then to enable efficient search, a coarsening strategy is proposed to continuously relax the search space, thus a differentiable search method can be adopted. Extensive experiments on six real-world datasets from three domains are conducted, and the results demonstrate the effectiveness and efficiency of the proposed framework1

PathSim is a widely used meta-path-based similarity in heterogeneous information networks. Numerous applications rely on the computation of PathSim, including similarity search and clustering. Computing PathSim scores on large graphs is computationally challenging due to its high time and storage complexity. In this paper, we propose to transform the problem of approximating the ground truth PathSim scores into a learning problem. We design an encoder-decoder based framework, NeuPath, where the algorithmic structure of PathSim is considered. Specifically, the encoder module identifies Top T optimized path instances, which can approximate the ground truth PathSim, and maps each path instance to an embedding vector. The decoder transforms each embedding vector into a scalar respectively, which identifies the similarity score. We perform extensive experiments on two real-world datasets in different domains, ACM and IMDB. Our results demonstrate that NeuPath performs better than state-of-the-art baselines in the PathSim approximation task and similarity search task.

Recent years have witnessed the popularity and success of graph neural networks (GNN) in various scenarios. To obtain data-specific GNN architectures, researchers turn to neural architecture search (NAS), which have made impressive success in discovering effective architectures in convolutional neural networks. However, it is non-trivial to apply NAS approaches to GNN due to challenges in search space design and expensive searching cost of existing NAS methods. In this work, to obtain the data-specific GNN architectures and address the computational challenges facing by NAS approaches, we propose a framework, which tries to Search to Aggregate NEighborhood (SANE), to automatically design data-specific GNN architectures. By designing a novel and expressive search space, we propose a differentiable search algorithm, which is more efficient than previous reinforcement learning based methods. Experimental results on four tasks and seven real-world datasets demonstrate the superiority of SANE compared to existing GNN models and NAS approaches in terms of effectiveness and efficiency.

In this paper, we propose a novel framework to automatically utilize task-dependent semantic information which is encoded in heterogeneous information networks (HINs). Specifically, we search for a meta graph, which can capture more complex semantic relations than a meta path, to determine how graph neural networks (GNNs) propagate messages along different types of edges. We formalize the problem within the framework of neural architecture search (NAS) and then perform the search in a differentiable manner. We design an expressive search space in the form of a directed acyclic graph (DAG) to represent candidate meta graphs for a HIN, and we propose task-dependent type constraint to filter out those edge types along which message passing has no effect on the representations of nodes that are related to the downstream task. The size of the search space we define is huge, so we further propose a novel and efficient search algorithm to make the total search cost on a par with training a single GNN once. Compared with existing popular NAS algorithms, our proposed search algorithm improves the search efficiency. We conduct extensive experiments on different HINs and downstream tasks to evaluate our method, and experimental results show that our method can outperform state-of-the-art heterogeneous GNNs and also improves efficiency compared with those methods which can implicitly learn meta paths.

Collaborative filtering (CF) has been one of the most important and popular recommendation methods, which aims at predicting users’ preferences (ratings) based on their past behaviors. Recently, various types of side information beyond the explicit ratings users give to items, such as social connections among users and metadata of items, have been introduced into CF and shown to be useful for improving recommendation performance. However, previous works process different types of information separately, thus failing to capture the correlations that might exist across them. To address this problem, in this work, we study the application of heterogeneous information network (HIN), which offers a unifying and flexible representation of different types of side information, to enhance CF-based recommendation methods. However, we face challenging issues in HIN-based recommendation, i.e., how to capture similarities of complex semantics between users and items in a HIN, and how to effectively fuse these similarities to improve final recommendation performance. To address these issues, we apply metagraph to similarity computation and solve the information fusion problem with a “matrix factorization (MF) + factorization machine (FM)” framework. For the MF part, we obtain the user-item similarity matrix from each metagraph and then apply low-rank matrix approximation to obtain latent features for both users and items. For the FM part, we apply FM with Group lasso (FMG) on the features obtained from the MF part to train the recommending model and, at the same time, identify the useful metagraphs. Besides FMG, a two-stage method, we further propose an end-to-end method, hierarchical attention fusing, to fuse metagraph-based similarities for the final recommendation. Experimental results on four large real-world datasets show that the two proposed frameworks significantly outperform existing state-of-the-art methods in terms of recommendation performance.

PageRank has been widely used to measure the authority or the influence of a user in social networks. However, conventional PageRank only makes use of edge-based relations, which represent first-order relations between two connected nodes. It ignores higher-order relations that may exist between nodes. In this article, we propose a novel framework, motif-based PageRank (MPR), to incorporate higher-order relations into the conventional PageRank computation. Motifs are subgraphs consisting of a small number of nodes. We use motifs to capture higher-order relations between nodes in a network and introduce two methods, one linear and one non-linear, to combine first-order and higher-order relations in PageRank computation. We conduct extensive experiments on three real-world networks, namely, DBLP, Epinions, and Ciao. We study different types of motifs, including 3-node simple and anchor motifs, 4-node and 5-node motifs. Besides using single motif, we also run MPR with ensemble of multiple motifs. We also design a learning task to evaluate the abilities of authority prediction with motif-based features. All experimental results demonstrate that MPR can significantly improve the performance of user ranking in social networks compared to the baseline methods.

In recent years, embedding models based on skip-gram algorithm have been widely applied to real-world recommendation systems (RSs). When designing embedding-based methods for recommendation at Taobao, there are three main challenges: scalability, sparsity and cold start. The first problem is inherently caused by the extremely large numbers of users and items (in the order of billions), while the remaining two problems are caused by the fact that most items have only very few (or none at all) user interactions. To address these challenges, in this work, we present a flexible and highly scalable Side Information (SI) enhanced Skip-Gram (SISG) framework, which is deployed at Taobao. SISG overcomes the drawbacks of existing embedding-based models by modeling user metadata and capturing asymmetries of user behavior. Furthermore, as training SISG can be performed using any SGNS implementation, we present our production deployment of SISG on a custom-built word2vec engine, which allows us to compute item and SI embedding vectors for billion-scale sets of products in a join semantic space on a daily basis. Finally, using offline and online experiments we demonstrate the significant superiority of SISG over our previously deployed framework, EGES, and a well-tuned CF, as well as present evidence supporting our scalability claims.

In this paper, we study the fundamental problem of random walk for network embedding. We propose to use non-Markovian random walk, variants of vertex-reinforced random walk (VRRW), to fully use the history of a random walk path. To solve the getting stuck problem of VRRW, we introduce an exploitation-exploration mechanism to help the random walk jump out of the stuck set. The new random walk algorithms share the same convergence property of VRRW and thus can be used to learn stable network embeddings. Experimental results on two link prediction benchmark datasets and three node classification benchmark datasets show that our proposed approach reinforce2vec can outperform state-of-the-art random walk based embedding methods by a large margin.

Industrial recommender systems have embraced deep learning algorithms for building intelligent systems to make accurate recommendations. At its core, deep learning offers powerful ability for learning representations from data, especially for user and item representations. Existing deep learning-based models usually represent a user by one representation vector, which is usually insufficient to capture diverse interests for large-scale users in practice. In this paper, we approach the learning of user representations from a different view, by representing a user with multiple representation vectors encoding the different aspects of the user's interests. To this end, we propose the Multi-Interest Network with Dynamic routing (MIND) for learning user representations in recommender systems. Specifically, we design a multi-interest extractor layer based on the recently proposed dynamic routing mechanism, which is applicable for modeling and extracting diverse interests from user's behaviors. Furthermore, a technique named label-aware attention is proposed to help the learning process of user representations. Through extensive experiments on several public benchmarks and one large-scale industrial dataset from Tmall, we demonstrate that MIND can achieve superior performance than state-of-the-art methods in terms of recommendation accuracy. Currently, MIND has been deployed for handling major online traffic at the homepage on Mobile Tmall App.

Heterogeneous Information Networks (HIN) has been widely used in recommender systems (RSs). In previous HIN-based RSs, meta-path is used to compute the similarity between users and items. However, existing meta-path based methods only consider first-order relations, ignoring higher-order relations among the nodes ofsame type, captured bymotifs. In this paper, we propose to use motifs to capture higher-order relations among nodes of same type in a HIN and develop the motif-enhanced meta-path (MEMP) to combine motif-based higher-order relations with edge-based first-order relations. With MEMP-based similarities between users and items, we design a recommending model MoHINRec, and experimental results on two real-world datasets, Epinions and CiaoDVD, demonstrate its superiority over existing HIN-based RS methods.

An effective content recommendation in modern social media platforms should benefit both creators to bring genuine benefits to them and consumers to help them get really interesting content. In this paper, we propose a model called Social Explorative Attention Network (SEAN) for content recommendation. SEAN uses a personalized content recommendation model to encourage personal interests driven recommendation. Moreover, SEAN allows the personalization factors to attend to users' higher-order friends on the social network to improve the accuracy and diversity of recommendation results. Constructing two datasets from a popular decentralized content distribution platform, Steemit, we compare SEAN with state-of-the-art CF and content based recommendation approaches. Experimental results demonstrate the effectiveness of SEAN in terms of both Gini coefficients for recommendation equality and F1 scores for recommendation performance.

Recommender systems (RSs) have been the most important technology for increasing the business in Taobao, the largest online consumer-to-consumer (C2C) platform in China. There are three major challenges facing RS in Taobao: scalability, sparsity and cold start. In this paper, we present our technical solutions to address these three challenges. The methods are based on a well-known graph embedding framework. We first construct an item graph from users' behavior history, and learn the embeddings of all items in the graph. The item embeddings are employed to compute pairwise similarities between all items, which are then used in the recommendation process. To alleviate the sparsity and cold start problems, side information is incorporated into the graph embedding framework. We propose two aggregation methods to integrate the embeddings of items and the corresponding side information. Experimental results from offline experiments show that methods incorporating side information are superior to those that do not. Further, we describe the platform upon which the embedding methods are deployed and the workflow to process the billion-scale data in Taobao. Using A/B test, we show that the online Click-Through-Rates (CTRs) are improved comparing to the previous collaborative filtering based methods widely used in Taobao, further demonstrating the effectiveness and feasibility of our proposed methods in Taobao's live production environment.

Matrix Factorization (MF) is a very popular method for recommendation systems. It assumes that the underneath rating matrix is low-rank. However, this assumption can be too restrictive to capture complex relationships and interactions among users and items. Recently, Local LOw-Rank Matrix Approximation (LLORMA) has been shown to be very successful in addressing this issue. It just assumes the rating matrix is composed of a number of low-rank submatrices constructed from subsets of similar users and items. Although LLORMA outperforms MF, how to construct such submatrices remains a big problem. Motivated by the availability of rich social connections in today's recommendation systems, we propose a novel framework, i.e., Social LOcal low-rank Matrix Approximation (SLOMA), to address this problem. To the best of our knowledge, SLOMA is the first work to incorporate social connections into the local low-rank framework. Furthermore, we enhance SLOMA by applying social regularization to submatrices factorization, denoted as SLOMA++. Therefore, the proposed model can benefit from both social recommendation and the local low-rank assumption. Experimental results from two real-world datasets, Yelp and Douban, demonstrate the superiority of the proposed models over LLORMA and MF.

Heterogeneous Information Network (HIN) is a natural and general representation of data in modern large commercial recommender systems which involve heterogeneous types of data. HIN based recommenders face two problems: how to represent the high-level semantics of recommendations and how to fuse the heterogeneous information to make recommendations. In this paper, we solve the two problems by first introducing the concept of meta-graph to HIN-based recommendation, and then solving the information fusion problem with a "matrix factorization (MF) + factorization machine (FM)" approach. For the similarities generated by each meta-graph, we perform standard MF to generate latent features for both users and items. With different meta-graph based features, we propose to use FM with Group lasso (FMG) to automatically learn from the observed ratings to effectively select useful meta-graph based features. Experimental results on two real-world datasets, Amazon and Yelp, show the effectiveness of our approach compared to state-of-the-art FM and other HIN-based recommendation algorithms.