Low-rank adaptations (LoRA) are widely used to fine-tune large models across various domains for specific downstream tasks. While task-specific LoRAs are often available, concerns about data privacy and intellectual property can restrict access to training data, limiting the acquisition of a multi-task model through gradient-based training. In response, LoRA merging presents an effective solution by combining multiple LoRAs into a unified adapter while maintaining data privacy. Prior works on LoRA merging primarily frame it as an optimization problem, yet these approaches face several limitations, including the rough assumption about input features utilized in optimization, massive sample requirements, and the unbalanced optimization objective. These limitations can significantly degrade performance. To address these, we propose a novel optimization-based method, named IterIS: 1) We formulate LoRA merging as an advanced optimization problem to mitigate the rough assumption. Additionally, we employ an iterative inference-solving framework in our algorithm. It can progressively refine the optimization objective for improved performance. 2) We introduce an efficient regularization term to reduce the need for massive sample requirements (requiring only 1-5% of the unlabeled samples compared to prior methods). 3) We utilize adaptive weights in the optimization objective to mitigate potential unbalances in LoRA merging process. Our method demonstrates significant improvements over multiple baselines and state-of-the-art methods in composing tasks for text-to-image diffusion, vision-language models, and large language models. Furthermore, our layer-wise algorithm can achieve convergence with minimal steps, ensuring efficiency in both memory and computation.

In the era of large foundation models, data has become a crucial component in building high-performance AI systems. As the demand for high-quality and large-scale data continues to rise, data copyright protection is attracting increasing attention. In this work, we explore the problem of data watermarking for sequential recommender systems, where a watermark is embedded into the target dataset and can be detected in models trained on that dataset. We focus on two settings: dataset watermarking, which protects the ownership of the entire dataset, and user watermarking, which safeguards the data of individual users. We present a method named Dataset Watermarking for Recommender Systems (DWRS) to address them. We define the watermark as a sequence of consecutive items inserted into normal users' interaction sequences. We define a Receptive Field (RF) to guide the inserting process to facilitate the memorization of the watermark. Extensive experiments on five representative sequential recommendation models and three benchmark datasets demonstrate the effectiveness of DWRS in protecting data copyright while preserving model utility.

Recommender systems embody significant commercial value and represent crucial intellectual property. However, the integrity of these systems is constantly challenged by malicious actors seeking to steal their underlying models. Safeguarding against such threats is paramount to upholding the rights and interests of the model owner. While model watermarking has emerged as a potent defense mechanism in various domains, its direct application to recommender systems remains unexplored and non-trivial. In this paper, we address this gap by introducing Autoregressive Out-of-distribution Watermarking (AOW), a novel technique tailored specifically for recommender systems. Our approach entails selecting an initial item and querying it through the oracle model, followed by the selection of subsequent items with small prediction scores. This iterative process generates a watermark sequence autoregressively, which is then ingrained into the model's memory through training. To assess the efficacy of the watermark, the model is tasked with predicting the subsequent item given a truncated watermark sequence. Through extensive experimentation and analysis, we demonstrate the superior performance and robust properties of AOW. Notably, our watermarking technique exhibits high-confidence extraction capabilities and maintains effectiveness even in the face of distillation and fine-tuning processes.

The robustness of recommender systems has become a prominent topic within the research community. Numerous adversarial attacks have been proposed, but most of them rely on extensive prior knowledge, such as all the white-box attacks or most of the black-box attacks which assume that certain external knowledge is available. Among these attacks, the model extraction attack stands out as a promising and practical method, involving training a surrogate model by repeatedly querying the target model. However, there is a significant gap in the existing literature when it comes to defending against model extraction attacks on recommender systems. In this paper, we introduce Gradient-based Ranking Optimization (GRO), which is the first defense strategy designed to counter such attacks. We formalize the defense as an optimization problem, aiming to minimize the loss of the protected target model while maximizing the loss of the attacker's surrogate model. Since top-k ranking lists are non-differentiable, we transform them into swap matrices which are instead differentiable. These swap matrices serve as input to a student model that emulates the surrogate model's behavior. By back-propagating the loss of the student model, we obtain gradients for the swap matrices. These gradients are used to compute a swap loss, which maximizes the loss of the student model. We conducted experiments on three benchmark datasets to evaluate the performance of GRO, and the results demonstrate its superior effectiveness in defending against model extraction attacks.

Nowadays, many dynamic recommendations still suffer from the insufficiency of finding user online interest evolving patterns because of those complicated interactions. In general, each interaction is usually impacted by multiple underlying reasons, which needs us to open the “box” of each interaction instance instead of simply treating them as a pair-wise link. Besides, different users usually perform differently for their long-term and short-term tastes, leaving traditional sequential models far from personalized. In this article, we propose a novel recommendation model based on Graph Diffusion and Ebbinghaus Curve. Specifically, to explore the underline reasons for different interactions, we explore an underlying sub-graph for each interaction and find important reasoning paths within the sub-graph via a well-designed graph diffusion method. To capture users’ personalized strategies on long-term and short-term tastes, we are inspired by the Ebbinghaus Curve, which can naturally describe users’ memory patterns, and design an effective neural network to process users’ evolving behaviors. We conduct extensive experiments on four real-world datasets and the results further confirm the superiority of our model compared with existing state-of-the-art baselines.

Compared with only pursuing recommendation accuracy, the explainability of a recommendation model has drawn more attention in recent years. Many graph-based recommendations resort to informative paths with the attention mechanism for the explanation. Unfortunately, these attention weights are intentionally designed for model accuracy but not explainability. Recently, some researchers have started to question attention-based explainability because the attention weights are unstable for different reproductions, and they may not always align with human intuition. Inspired by the counterfactual reasoning from causality learning theory, we propose a novel explainable framework targeting path-based recommendations, wherein the explainable weights of paths are learned to replace attention weights. Specifically, we design two counterfactual reasoning algorithms from both path representation and path topological structure perspectives. Moreover, unlike traditional case studies, we also propose a package of explainability evaluation solutions with both qualitative and quantitative methods. We conduct extensive experiments on four real-world datasets, the results of which further demonstrate the effectiveness and reliability of our method.

Graph Contrastive Learning (GCL) stands as a potent framework for unsupervised graph representation learning that has gained traction across numerous graph learning applications. The effectiveness of GCL relies on generating high-quality contrasting samples, enhancing the model’s ability to discern graph semantics. However, the prevailing GCL methods face two key challenges: 1) introducing noise during graph augmentations and 2) requiring additional storage for generated samples, which degrade the model performance. In this paper, we propose novel approaches, GKCL (i.e., Graph Knowledge Contrastive Learning) and DGKCL (i.e., Distilled Graph Knowledge Contrastive Learning), that leverage multi-level graph knowledge to create noise-free contrasting pairs. This framework not only addresses the noise-related challenges but also circumvents excessive storage demands. Furthermore, our method incorporates a knowledge distillation component to optimize the trained embedding tables, reducing the model’s scale while ensuring superior performance, particularly for the scenarios with smaller embedding sizes. Comprehensive experimental evaluations on three public benchmark datasets underscore the merits of our proposed method and elucidate its properties, which primarily reflect the performance of the proposed method equipped with different embedding sizes and how the distillation weight affects the overall performance.

Graph contrastive learning (GCL) has emerged as a potent technology for numerous graph learning tasks. It has been successfully applied to real-world recommender systems, where the contrastive loss and the downstream recommendation objectives are always combined to form the overall objective function. Such a strategy is inconsistent with the original GCL paradigm, where graph embeddings are pre-trained without involving downstream training objectives. In this paper, we innovatively propose a prompt-enhanced framework for GCL-based recommender systems, namely CPTPP, which can fully leverage the advantages of the original GCL protocol through prompt tuning. Specifically, we first summarise user profiles in graph recommender systems to automatically generate personalized user prompts. These prompts will then be combined with pre-trained user embeddings to conduct prompt-tuning in downstream tasks, thereby narrowing the distinct targets between pre-training and downstream tasks. Extensive experiments on three benchmark datasets validate the effectiveness of CPTPP against state-of-the-art baselines. A further visualization experiment demonstrates that user embeddings generated by CPTPP have a more uniform distribution, indicating a better capacity to model the diversity of user preferences. The implementation code is available online to ease reproducibility: https://anonymous.4open.science/r/CPTPP-F8F4

Graph contrastive learning has emerged as a powerful unsupervised graph representation learning tool. The key to the success of graph contrastive learning is to acquire high-quality positive and negative samples as contrasting pairs to learn the underlying structural semantics of the input graph. Recent works usually sample negative samples from the same training batch with the positive samples or from an external irrelevant graph. However, a significant limitation lies in such strategies: the unavoidable problem of sampling false negative samples. In this paper, we propose a novel method to utilize Counterfactual mechanism to generate artificial hard negative samples for Graph Contrastive learning, namely CGC. We utilize a counterfactual mechanism to produce hard negative samples, ensuring that the generated samples are similar but have labels that differ from the positive sample. The proposed method achieves satisfying results on several datasets. It outperforms some traditional unsupervised graph learning methods and some SOTA graph contrastive learning methods. We also conducted some supplementary experiments to illustrate the proposed method, including the performances of CGC with different hard negative samples and evaluations for hard negative samples generated with different similarity measurements. The implementation code is available online to ease reproducibility1.

Product reviews on e-commerce platforms play a critical role in shaping users’ purchasing decisions. Unfortunately, online reviews sometimes can be intentionally misleading to manipulate the ecosystem. To date, existing methods to automatically detect “spam reviews” either focus on sophisticated feature engineering with traditional classification models or rely on tuning neural networks with aggregated features. In this article, we develop a novel graph-based model, namely, graph-aware deep fusion networks (GDFNs) that use information from relevant metadata (review text, features of users, and items) and relational data (network) to capture the semantic information from their complex heterogeneous interactions via graph convolutional networks (GCNs). Besides, GDFN also uses a novel fusion technique to synthesize low- and high-order interactions with propagated information across multiple review-related subgraphs. Extensive experiments on publicly available datasets show that our proposed model is effective and outperforms several strong state-of-the-art baselines.

Recent advances in path-based explainable recommendation systems have attracted increasing attention thanks to the rich information from knowledge graphs. Most existing explainable recommendations only utilize static knowledge graphs and ignore the dynamic user-item evolutions, leading to less convincing and inaccurate explanations. Although some works boost the performance and explainability of recommendations through modeling the user's temporal sequential behavior, most of them either only focus on modeling the user's sequential interactions within a path or independently and separately of the recommendation mechanism. Moreover, some path-based explainable recommendations use random selection or traditional machine learning methods to decrease the volume of explainable paths, which cannot guarantee high quality of the explainable paths for the recommendation. To deal with the problem, recent path exploration use reinforcement learning to improve diversity and quality. However, unsupervised training leads to low-efficiency path exploration. Therefore, we propose a novelTemporalMeta-path GuidedExplainableRecommendation leveragingReinforcementLearning (TMER-RL), which utilizes supervised reinforcement learning to explore item-item paths between consecutive items with attention mechanisms to sequentially model dynamic user-item evolutions on a dynamic knowledge graph for the explainable recommendation. Extensive evaluations of TMER-RL on two real-world datasets show state-of-the-art performance compared to recent strong baselines.

Recently, deep learning techniques have yielded immense success on recommender systems. However, one weakness of most deep methods is that, users/items mutual semantic relationships, which are latent in the user-item interactions, are not distilled out explicitly. Moreover, most methods have been primarily focused on representation learning in euclidean geometry. Since recent studies have shown that the bipartite graph structure has the non-euclidean latent anatomy, euclidean embeddings may suffer from a certain degree of distortion. In this work, we presentHyperbolicNeuralCollaborativeRecommender (HNCR), a deep hyperbolic representation learning method that exploits mutual semantic relationships among users/items for collaborative filtering tasks. HNCR first introduces a neighbor construction strategy to build user and item semantic neighborhoods. Then HNCR develops a framework based on deep learning and hyperbolic geometry to integrate constructed neighborhoods into recommendation. To evaluate our method, we conduct experiments on the four datasets. Experimental results show the superiority of HNCR compared with its euclidean counterpart and state-of-the-art recommendation baselines. The results also indicate that hyperbolic representations can reflect meaningful data insights.

Signed link prediction in social networks aims to reveal the underlying relationships (i.e., links) among users (i.e., nodes) given their existing positive and negative interactions observed. Most of the prior efforts are devoted to learning node embeddings with graph neural networks (GNNs), which preserve the signed network topology by message-passing along edges to facilitate the downstream link prediction task. Nevertheless, the existing graph-based approaches could hardly provide human-intelligible explanations for the following three questions: (1) which neighbors to aggregate, (2) which path to propagate along, and (3) which social theory to follow in the learning process. To answer the aforementioned questions, in this paper, we investigate how to reconcile thebalanceandstatussocial rules with information theory and develop a unified framework, termed as Signed Infomax Hyperbolic Graph (SIHG). By maximizing the mutual information between edge polarities and node embeddings, one can identify the most representative neighboring nodes that support the inference of edge sign. Different from existing GNNs that could only group features of friends in the subspace, the proposed SIHG incorporates the signed attention module, which is also capable of pushing hostile users far away from each other to preserve the geometry of antagonism. The polarity of the learned edge attention maps, in turn, provides interpretations of the social theories used in each aggregation. In order to model high-order user relations and complex hierarchies, the node embeddings are projected and measured in a hyperbolic space with a lower distortion. Extensive experiments on four signed network benchmarks demonstrate that the proposed SIHG framework significantly outperforms the state-of-the-arts in signed link prediction.

Online social networks have greatly facilitated our lives but have also propagated the spreading of rumours. Traditional works mostly find rumors from content, but content can be strategically manipulated to evade such detection, making these methods brittle. To improve the accuracy and robustness of rumor detection, we propose to integrate and exploit the content, propagation structure, and temporal relations because information in the networks always spreads dynamically with significant structures. In this paper, we propose a novel rumor detection framework in online temporal networks via structure learning. Specifically, to exploit the propagation structure, we propose a novel hyperedge walking strategy on a meta-hyperedge graph to learn the representations of sub-structures in the networks. Then a hyperedge expansion method is proposed to generate more global structural features. The expanded hyperedges are more hierarchical, making the learned structural embeddings more expressive. To make full use of content, we design a hypergraph learning model using hyperedge expansion to fuse node content with structural features and generate comprehensive representations for the entire graph. To exploit temporal relations, we design a masked temporal attention unit for learning the evolving patterns of the network. Extensive evaluations with six state-of-the-art baselines on two real-world datasets demonstrate the superiority of our solution.

Predicting future events in dynamic knowledge graphs has attracted significant attention. Existing work models the historical information in a holistic way, which achieves satisfactory performance. However, in real-world scenarios, the influence of historical information on future events is changing over time. Therefore, it is difficult to distinguish the historical information of different roles by invariably embedding historical entities with simple vector stacking. Furthermore, it is laborious to explicitly learn a distributed representation of each historical repetitive fact at different timestamps. This poses a challenge to the widely adopted codec-based architectures. In this paper, we propose a novel model for predicting future events, namely Distributed Attention Network (DA-Net). Rather than obtaining the fixed representations of historical events, DA-Net attempts to learn the distributed attention of future events on repetitive facts at different historical timestamps inspired by human cognitive theory. In human cognitive theory, when humans make a decision, similar historical events are replayed during memory recall. Based on memory, the original intention is adjusted according to their recent knowledge developments, making the action more reasonable to the context. Experiments on four benchmark datasets demonstrate a substantial improvement of DA-Net on multiple evaluation metrics.

Medication recommendation is a crucial task for intelligent healthcare systems. Previous studies mainly recommend medications with electronic health records (EHRs). However, some details of interactions between doctors and patients may be ignored or omitted in EHRs, which are essential for automatic medication recommendation. Therefore, we make the first attempt to recommend medications with the conversations between doctors and patients. In this work, we construct DIALMED, the first high-quality dataset for medical dialogue-based medication recommendation task. It contains 11, 996 medical dialogues related to 16 common diseases from 3 departments and 70 corresponding common medications. Furthermore, we propose a Dialogue structure and Disease knowledge aware Network (DDN), where a QA Dialogue Graph mechanism is designed to model the dialogue structure and the knowledge graph is used to introduce external disease knowledge. The extensive experimental results demonstrate that the proposed method is a promising solution to recommend medications with medical dialogues. The dataset and code are available at https://github.com/f-window/DialMed.

Off-policy learning has drawn huge attention in recommender systems (RS), which provides an opportunity for reinforcement learning to abandon the expensive online training. However, off-policy learning from logged data suffers biases caused by the policy shift between the target policy and the logging policy. Consequently, most off-policy learning resorts to inverse propensity scoring (IPS) which however tends to be over-fitted over exposed (or recommended) items and thus fails to explore unexposed items.

Collaborative filtering is a central task in a broad range of recommender systems. As traditional methods train latent variables for user/item individuals under a transductive setting, it requires re-training for out-of-sample inferences. Inductive matrix completion (IMC) solves this problem by learning transformation functions upon engineered features, but it sacrifices model expressiveness and highly depends on feature qualities. In this paper, we propose Geometric Inductive Matrix Completion (GIMC) by introducing hyperbolic geometry and a unified message passing scheme into this generic task. The proposed method is the earliest attempt utilizing capacious hyperbolic space to enhance the capacity of IMC. It is the first work defining continuous explicit feedback prediction within non-Euclidean space by introducing hyperbolic regression for vertex interactions. This is also the first to provide comprehensive evidence that edge semantics can significantly improve recommendations, which is ignored by previous works. The proposed method outperforms the state-of-the-art algorithms with less than 1% parameters compared to its transductive counterparts. Extensive analysis and ablation studies are conducted to reveal the design considerations and practicability for a positive impact to the research community.

In recent years, graph neural networks (GNNs) have emerged as a successful tool in a variety of graph-related applications. However, the performance of GNNs can be deteriorated when noisy connections occur in the original graph structures; besides, the dependence on explicit structures prevents GNNs from being applied to general unstructured scenarios. To address these issues, recently emerged deep graph structure learning (GSL) methods propose to jointly optimize the graph structure along with GNN under the supervision of a node classification task. Nonetheless, these methods focus on a supervised learning scenario, which leads to several problems, i.e., the reliance on labels, the bias of edge distribution, and the limitation on application tasks. In this paper, we propose a more practical GSL paradigm, unsupervised graph structure learning, where the learned graph topology is optimized by data itself without any external guidance (i.e., labels). To solve the unsupervised GSL problem, we propose a novel StrUcture Bootstrapping contrastive LearnIng fraMEwork (SUBLIME for abbreviation) with the aid of self-supervised contrastive learning. Specifically, we generate a learning target from the original data as an “anchor graph”, and use a contrastive loss to maximize the agreement between the anchor graph and the learned graph. To provide persistent guidance, we design a novel bootstrapping mechanism that upgrades the anchor graph with learned structures during model learning. We also design a series of graph learners and post-processing schemes to model the structures to learn. Extensive experiments on eight benchmark datasets demonstrate the significant effectiveness of our proposed SUBLIME and high quality of the optimized graphs.

Unsupervised graph representation learning has emerged as a powerful tool to address real-world problems and achieves huge success in the graph learning domain. Graph contrastive learning is one of the unsupervised graph representation learning methods, which recently attracts attention from researchers and has achieved state-of-the-art performances on various tasks. The key to the success of graph contrastive learning is to construct proper contrasting pairs to acquire the underlying structural semantics of the graph. However, this key part is not fully explored currently, most of the ways generating contrasting pairs focus on augmenting or perturbating graph structures to obtain different views of the input graph. But such strategies could degrade the performances via adding noise into the graph, which may narrow down the field of the applications of graph contrastive learning. In this paper, we propose a novel graph contrastive learning method, namely Dual Space Graph Contrastive (DSGC) Learning, to conduct graph contrastive learning among views generated in different spaces including the hyperbolic space and the Euclidean space. Since both spaces have their own advantages to represent graph data in the embedding spaces, we hope to utilize graph contrastive learning to bridge the spaces and leverage advantages from both sides. The comparison experiment results show that DSGC achieves competitive or better performances among all the datasets. In addition, we conduct extensive experiments to analyze the impact of different graph encoders on DSGC, giving insights about how to better leverage the advantages of contrastive learning between different spaces.

Graph contrastive learning is the state-of-the-art unsupervised graph representation learning framework and has shown comparable performance with supervised approaches. However, evaluating whether the graph contrastive learning is robust to adversarial attacks is still an open problem because most existing graph adversarial attacks are supervised models, which means they heavily rely on labels and can only be used to evaluate the graph contrastive learning in a specific scenario. For unsupervised graph representation methods such as graph contrastive learning, it is difficult to acquire labels in real-world scenarios, making traditional supervised graph attack methods difficult to be applied to test their robustness. In this paper, we propose a novel unsupervised gradient-based adversarial attack that does not rely on labels for graph contrastive learning. We compute the gradients of the adjacency matrices of the two views and flip the edges with gradient ascent to maximize the contrastive loss. In this way, we can fully use multiple views generated by the graph contrastive learning models and pick the most informative edges without knowing their labels, and therefore can promisingly support our model adapted to more kinds of downstream tasks. Extensive experiments show that our attack outperforms unsupervised baseline attacks and has comparable performance with supervised attacks in multiple downstream tasks including node classification and link prediction. We further show that our attack can be transferred to other graph representation models as well.

With the prevalence of online social platforms, social recommendation has emerged as a promising direction that leverages the social network among users to enhance recommendation performance. However, the available social relations among users are usually extremely sparse and noisy, which may lead to inferior recommendation performance. To alleviate this problem, this paper novelly exploits the implicit higher-order social influence and dependencies among users to enhance social recommendation. In this paper, we propose a novel embedding method for general bipartite graphs, which defines inter-class message passing between explicit relations and intra-class message passing between implicit higher-order relations via a novel sequential modelling paradigm. Inspired by recent advances in self-attention-based sequential modelling, the proposed model features a self-attentive representation learning mechanism for implicit user-user relations. Moreover, this paper also explores the inductive embedding learning for social recommendation problems to improve the recommendation performance in cold-start settings. The proposed inductive learning paradigm for social recommendation enables embedding inference for those cold-start users and items (unseen during training) as long as they are linked to existing nodes in the original network. Extensive experiments on real-world datasets demonstrate the superiority of our method and suggest that higher-order implicit relationship among users is beneficial to improving social recommendation.

Hypergraphs have been becoming a popular choice to model complex, non-pairwise, and higher-order interactions for recommender systems. However, compared with traditional graph-based methods, the constructed hypergraphs are usually much sparser, which leads to a dilemma when balancing the benefits of hypergraphs and the modelling difficulty. Moreover, existing sequential hypergraph recommendation overlooks the temporal modelling among user relationships, which neglects rich social signals from the recommendation data. To tackle the above shortcomings of the existing hypergraph-based sequential recommendations, we propose a novel architecture named Hyperbolic Hypergraph representation learning method for Sequential Recommendation (H2SeqRec) with the pre-training phase. Specifically, we design three self-supervised tasks to obtain the pre-training item embeddings to feed or fuse into the following recommendation architecture (with two ways to use the pre-trained embeddings). In the recommendation phase, we learn multi-scale item embeddings via a hierarchical structure to capture multiple time-span information. To alleviate the negative impact of sparse hypergraphs, we utilize a hyperbolic space-based hypergraph convolutional neural network to learn the dynamic item embeddings. Also, we design an item enhancement module to capture dynamic social information at each timestamp to improve effectiveness. Extensive experiments are conducted on two real-world datasets to prove the effectiveness and high performance of the model.

Advertising is critical to many online e-commerce platforms such as e-Bay and Amazon. One of the important signals that these platforms rely upon is the click-through rate (CTR) prediction. The recent popularity of multi-modal sharing platforms such as TikTok has led to an increased interest in online micro-videos. It is, therefore, useful to consider micro-videos to help a merchant target micro-video advertising better and find users' favourites to enhance user experience. Existing works on CTR prediction largely exploit unimodal content to learn item representations. A relatively minimal effort has been made to leverage multi-modal information exchange among users and items. We propose a model to exploit the temporal user-item interactions to guide the representation learning with multi-modal features, and further predict the user click rate of the micro-video item. We design a Hypergraph Click-Through Rate prediction framework (HyperCTR) built upon the hyperedge notion of hypergraph neural networks, which can yield modal-specific representations of users and micro-videos to better capture user preferences. We construct a time-aware user-item bipartite network with multi-modal information and enrich the representation of each user and item with the generated interests-based user hypergraph and item hypergraph. Through extensive experiments on three public datasets, we demonstrate that our proposed model significantly outperforms various state-of-the-art methods.

Hashtag, a product of user tagging behavior, which can well describe the semantics of the user-generated content personally over social network applications, e.g., the recently popular micro-videos. Hashtags have been widely used to facilitate various micro-video retrieval scenarios, such as search engine and categorization. In order to leverage hashtags on micro-media platform for effective e-commerce marketing campaign, there is a demand from e-commerce industry to develop a mapping algorithm bridging its categories and micro-video hashtags. In this demo paper, we therefore proposed a novel solution called TagPick that incorporates clues from all user behavior metadata (hashtags, interactions, multimedia information) as well as relational data (graph-based network) into a unified system to reveal the correlation between e-commerce categories and hashtags in industrial scenarios. In particular, we provide a tag-level popularity strategy to recommend the relevant hashtags for e-Commerce platform (e.g., eBay).

User purchasing prediction with multi-behavior information remains a challenging problem for current recommendation systems. Various methods have been proposed to address it via leveraging the advantages of graph neural networks (GNNs) or multi-task learning. However, most existing works do not take the complex dependencies among different behaviors of users into consideration. They utilize simple and fixed schemes, like neighborhood information aggregation or mathematical calculation of vectors, to fuse the embeddings of different user behaviors to obtain a unified embedding to represent a user’s behavioral patterns which will be used in downstream recommendation tasks. To tackle the challenge, in this paper, we first propose the concept of hyper meta-path to construct hyper meta-paths or hyper meta-graphs to explicitly illustrate the dependencies among different behaviors of a user. How to obtain a unified embedding for a user from hyper meta-paths and avoid the previously mentioned limitations simultaneously is critical. Thanks to the recent success of graph contrastive learning, we leverage it to learn embeddings of user behavior patterns adaptively instead of assigning a fixed scheme to understand the dependencies among different behaviors. A new graph contrastive learning based framework is proposed by coupling with hyper meta-paths, namely HMG-CR, which consistently and significantly outperforms all baselines in extensive comparison experiments.

Hyperbolic space and hyperbolic embeddings are becoming a popular research field for recommender systems. However, it is not clear under what circumstances the hyperbolic space should be considered. To fill this gap, This paper provides theoretical analysis and empirical results on when and where to use hyperbolic space and hyperbolic embeddings in recommender systems. Specifically, we answer the questions that which type of models and datasets are more suited for hyperbolic space, as well as which latent size to choose. We evaluate our answers by comparing the performance of Euclidean space and hyperbolic space on different latent space models in both general item recommendation domain and social recommendation domain, with 6 widely used datasets and different latent sizes. Additionally, we propose a new metric learning based recommendation method called SCML and its hyperbolic version HSCML. We evaluate our conclusions regarding hyperbolic space on SCML and show the state-of-the-art performance of hyperbolic space by comparing HSCML with other baseline methods.

Recent advances in path-based explainable recommendation systems have attracted increasing attention thanks to the rich information provided by knowledge graphs. Most existing explainable recommendation only utilizes static knowledge graph and ignores the dynamic user-item evolutions, leading to less convincing and inaccurate explanations. Although there are some works that realize that modelling user's temporal sequential behaviour could boost the performance and explainability of the recommender systems, most of them either only focus on modelling user's sequential interactions within a path or independently and separately of the recommendation mechanism. In this paper, we propose a novel Temporal Meta-path Guided Explainable Recommendation (TMER), which utilizes well-designed item-item path modelling between consecutive items with attention mechanisms to sequentially model dynamic user-item evolutions on dynamic knowledge graph for explainable recommendations. Compared with existing works that use heavy recurrent neural networks to model temporal information, we propose simple but effective neural networks to capture users' historical item features and path-based context to characterise next purchased item. Extensive evaluations of TMER on three real-world benchmark datasets show state-of-the-art performance compared against recent strong baselines.

Recently, graph neural networks have been widely used for network embedding because of their prominent performance in pairwise relationship learning. In the real world, a more natural and common situation is the coexistence of pairwise relationships and complex non-pairwise relationships, which is, however, rarely studied. In light of this, we propose a graph neural network-based representation learning framework for heterogeneous hypergraphs, an extension of conventional graphs, which can well characterize multiple non-pairwise relations. Our framework first projects the heterogeneous hypergraph into a series of snapshots and then we take the Wavelet basis to perform localized hypergraph convolution. Since the Wavelet basis is usually much sparser than the Fourier basis, we develop an efficient polynomial approximation to the basis to replace the time-consuming Laplacian decomposition. Extensive evaluations have been conducted and the experimental results show the superiority of our method. In addition to the standard tasks of network embedding evaluation such as node classification, we also apply our method to the task of spammers detection and the superior performance of our framework shows that relationships beyond pairwise are also advantageous in the spammer detection. To make our experiment repeatable, source codes and related datasets are available at https://xiangguosun.mystrikingly.com

Social linking prediction is one of the most fundamental problems in online social networks and has attracted researchers’ persistent attention. Most of the existing works predict unobserved links using graph neural networks (GNNs) to learn node embeddings upon pair-wise relations. Despite promising results given enough observed links, these models are still challenging to achieve heart-stirring performance when observed links are extremely limited. The main reason is that they only focus on the smoothness of node representations on pair-wise relations. Unfortunately, this assumption may fall when the networks do not have enough observed links to support it. To this end, we go beyond pair-wise relations and propose a new and novel framework using hypergraph neural networks with multi-level hyperedge distillation strategies. To break through the limitations of sparsely observed links, we introduce the hypergraph to uncover higher-level relations, which is exceptionally crucial to deduce unobserved links. A hypergraph allows one edge to connect multiple nodes, making it easier to learn better higher-level relations for link prediction. To overcome the restrictions of manually designed hypergraphs, which is constant in most hypergraph researches, we propose a new method to learn high-quality hyperedges using three novel hyperedges distillation strategies automatically. The generated hyperedges are hierarchical and follow the power-law distribution, which can significantly improve the link prediction performance. To predict unobserved links, we present a novel hypergraph neural networks named HNN. HNN takes the multi-level hypergraphs as input and makes the node embeddings smooth on hyperedges instead of pair-wise links only. Extensive evaluations on four real-world datasets demonstrate our model’s superior performance over state-of-the-art baselines, especially when the observed links are extremely reduced.

With the increasingly available electronic medical records (EMRs), disease prediction has recently gained immense research attention, where an accurate classifier needs to be trained to map the input prediction signals (e.g., symptoms, patient demographics, etc.) to the estimated diseases for each patient. However, existing machine learning-based solutions heavily rely on abundant manually labeled EMR training data to ensure satisfactory prediction results, impeding their performance in the existence of rare diseases that are subject to severe data scarcity. For each rare disease, the limited EMR data can hardly offer sufficient information for a model to correctly distinguish its identity from other diseases with similar clinical symptoms. Furthermore, most existing disease prediction approaches are based on the sequential EMRs collected for every patient and are unable to handle new patients without historical EMRs, reducing their real-life practicality. In this paper, we introduce an innovative model based on Graph Neural Networks (GNNs) for disease prediction, which utilizes external knowledge bases to augment the insufficient EMR data, and learns highly representative node embeddings for patients, diseases and symptoms from the medical concept graph and patient record graph respectively constructed from the medical knowledge base and EMRs. By aggregating information from directly connected neighbor nodes, the proposed neural graph encoder can effectively generate embeddings that capture knowledge from both data sources, and is able to inductively infer the embeddings for a new patient based on the symptoms reported in her/his EMRs to allow for accurate prediction on both general diseases and rare diseases. Extensive experiments on a real-world EMR dataset have demonstrated the state-of-the-art performance of our proposed model.

Obstructive Sleep Apnea (OSA) is a highly prevalent but inconspicuous disease that seriously jeopardizes the health of human beings. Polysomnography (PSG), the gold standard of detecting OSA, requires multiple specialized sensors for signal collection, hence patients have to physically visit hospitals and bear the costly treatment for a single detection. Recently, many single-sensor alternatives have been proposed to improve the cost efficiency and convenience. Among these methods, solutions based on RR-interval (i.e., the interval between two consecutive pulses) signals reach a satisfactory balance among comfort, portability and detection accuracy. In this paper, we advance RR-interval based OSA detection by considering its real-world practicality from energy perspectives. As photoplethysmogram (PPG) pulse sensors are commonly equipped on smart wrist-worn wearable devices (e.g., smart watches and wristbands), the energy efficiency of the detection model is crucial to fully support an overnight observation on patients. This creates challenges as the PPG sensors are unable to keep collecting continuous signals due to the limited battery capacity on smart wrist-worn devices. Therefore, we propose a novel Frequency Extraction Network (FENet), which can extract features from different frequency bands of the input RR-interval signals and generate continuous detection results with downsampled, discontinuous RR-interval signals. With the help of the one-to-multiple structure, FENet requires only one-third of the operation time of the PPG sensor, thus sharply cutting down the energy consumption and enabling overnight diagnosis. Experimental results on real OSA datasets reveal the state-of-the-art performance of FENet.

Stochastic blockmodel (SBM) is a widely used statistical network representation model, with good interpretability, expressiveness, generalization, and flexibility, which has become prevalent and important in the field of network science over the last years. However, learning an optimal SBM for a given network is an NP-hard problem. This results in significant limitations when it comes to applications of SBMs in large-scale networks, because of the significant computational overhead of existing SBM models, as well as their learning methods. Reducing the cost of SBM learning and making it scalable for handling large-scale networks, while maintaining the good theoretical properties of SBM, remains an unresolved problem. In this work, we address this challenging task from a novel perspective of model redefinition. We propose a novel redefined SBM with Poisson distribution and its block-wise learning algorithm that can efficiently analyse large-scale networks. Extensive validation conducted on both artificial and real-world data shows that our proposed method significantly outperforms the state-of-the-art methods in terms of a reasonable trade-off between accuracy and scalability. 1

Cross-platform account matching plays a significant role in social network analytics, and is beneficial for a wide range of applications. However, existing methods either heavily rely on high-quality user generated content (including user profiles) or suffer from data insufficiency problem if only focusing on network topology, which brings researchers into an insoluble dilemma of model selection. In this paper, to address this problem, we propose a novel framework that considers multi-level graph convolutions on both local network structure and hypergraph structure in a unified manner. The proposed method overcomes data insufficiency problem of existing work and does not necessarily rely on user demographic information. Moreover, to adapt the proposed method to be capable of handling large-scale social networks, we propose a two-phase space reconciliation mechanism to align the embedding spaces in both network partitioning based parallel training and account matching across different social networks. Extensive experiments have been conducted on two large-scale real-life social networks. The experimental results demonstrate that the proposed method outperforms the state-of-the-art models with a big margin.

Network embedding has been proven effective to learn low-dimensional vector representations for network vertices, and recently received a tremendous amount of research attention. However, most of existing methods for network embedding merely focus on preserving the first and second order proximities between nodes, and the important properties of node centrality are neglected. Various centrality measures such as Degree, Closeness, Betweenness, Eigenvector and PageRank centralities have been designed to measure the importance of individual nodes. In this paper, we focus on a novel yet unsolved problem that aims to learn low-dimensional continuous nodes representations that not only preserve the network structure, but also keep the centrality information. We propose a generalizable model, namely GraphCSC, that utilizes both linkage information and centrality information to learn low-dimensional vector representations for network vertices. The learned embeddings by GraphCSC are able to preserve different centrality information of nodes. In addition, we further propose GraphCSC-M, a more comprehensive model that can preserve different centrality information simultaneously through learning multiple centrality-specific embeddings, and a novel attentive multi-view learning approach is developed to compress multiple embeddings of one node into a compact vector representation. Extensive experiments have been conducted to demonstrate that our model is able to preserve different centrality information of nodes, and achieves better performance on several benchmark tasks compared with recent state-of-the-art network embedding methods.

The capability of extracting sequential patterns from the user-item interaction data is now becoming a key feature of recommender systems. Though it is important to capture the sequential effect, existing methods only focus on modelling the sparse item-wise sequential effect in user preference and only consider the homogeneous user interaction behaviors (i.e., a single type of user behavior). As a result, the data sparsity issue inevitably arises and makes the learned sequential patterns fragile and unreliable, impeding the sequential recommendation performance of existing methods. Hence, in this paper, we propose AIR, namely attentional intention-aware recommender systems to predict category-wise future user intention and collectively exploit the rich heterogeneous user interaction behaviors (i.e., multiple types of user behaviors). In AIR, we propose to represent user intention as an action-category tuple to discover category-wise sequential patterns and to capture varied effect of different types of actions for recommendation. A novel attentional recurrent neural network (ARNN) is proposed to model the intention migration effect and infer users' future intention. Besides, an intention-aware factorization machine (ITFM) is developed to perform intention-aware sequential recommendation. Experiments on two real-life datasets demonstrate the superiority and practicality of AIR in sequential top-k recommendation tasks.

On E-commerce platforms, understanding the relationships (e.g., substitute and complement) among products from user's explicit feedback, such as users' online transactions, is of great importance to boost extra sales. However, the significance of such relationships is usually neglected by existing recommender systems. In this paper, we propose a semisupervised deep embedding model, namely, Substitute Products Embedding Model (SPEM), which models the substitutable relationships between products by preserving the second-order proximity, negative first-order proximity and semantic similarity in a product co-purchasing graph based on user's purchasing behaviours. With SPEM, the learned representations of two substitutable products align closely in the latent embedding space. Extensive experiments on real-world datasets are conducted, and the results verify that our model outperforms state-of-the-art baselines.

Ride-hailing applications are becoming more and more popular for providing drivers and passengers with convenient ride services, especially in metropolises like Beijing or New York. To obtain the passengers' mobility patterns, the online platforms of ride services need to predict the number of passenger demands from one region to another in advance. We formulate this problem as an Origin-Destination Matrix Prediction (ODMP) problem. Though this problem is essential to large-scale providers of ride services for helping them make decisions and some providers have already put it forward in public, existing studies have not solved this problem well. One of the main reasons is that the ODMP problem is more challenging than the common demand prediction. Besides the number of demands in a region, it also requires the model to predict the destinations of them. In addition, data sparsity is a severe issue. To solve the problem effectively, we propose a unified model, Grid-Embedding based Multi-task Learning (GEML) which consists of two components focusing on spatial and temporal information respectively. The Grid-Embedding part is designed to model the spatial mobility patterns of passengers and neighboring relationships of different areas, the pre-weighted aggregator of which aims to sense the sparsity and range of data. The Multi-task Learning framework focuses on modeling temporal attributes and capturing several objectives of the ODMP problem. The evaluation of our model is conducted on real operational datasets from UCAR and Didi. The experimental results demonstrate the superiority of our GEML against the state-of-the-art approaches.

As a common strategy in sales-supply chains, the prediction of sales volume offers precious information for companies to achieve a healthy balance between supply and demand. In practice, the sales prediction task is formulated as a time series prediction problem which aims to predict the future sales volume for different products with the observation of various influential factors (e.g., brand, season, discount, etc.) and corresponding historical sales records. However, with the development of contemporary commercial markets, the dynamic interaction between influential factors with different semantic meanings becomes more subtle, causing challenges in fully capturing dependencies among these variables. Besides, though seeking similar trends from the history benefits the accuracy for the prediction of upcoming sales, existing methods hardly suit sales prediction tasks because the trends in sales time series are more irregular and complex. Hence, we gain insights from the encoder-decoder recurrent neural network (RNN) structure, and propose a novel framework named TADA to carry out trend alignment with dualattention, multi-task RNNs for sales prediction. In TADA, we innovatively divide the influential factors into internal feature and external feature, which are jointly modelled by a multi-task RNN encoder. In the decoding stage, TADA utilizes two attention mechanisms to compensate for the unknown states of influential factors in the future and adaptively align the upcoming trend with relevant historical trends to ensure precise sales prediction. Experimental results on two real-world datasets comprehensively show the superiority of TADA in sales prediction tasks against other state-of-the-art competitors.

Heterogenous information network embedding aims to embed heterogenous information networks (HINs) into low dimensional spaces, in which each vertex is represented as a low-dimensional vector, and both global and local network structures in the original space are preserved. However, most of existing heterogenous information network embedding models adopt the dot product to measure the proximity in the low dimensional space, and thus they can only preserve the first-order proximity and are insufficient to capture the global structure. Compared with homogenous information networks, there are multiple types of links (i.e., multiple relations) in HINs, and the link distribution w.r.t relations is highly skewed. To address the above challenging issues, we propose a novel heterogenous information network embedding model PME based on the metric learning to capture both first-order and second-order proximities in a unified way. To alleviate the potential geometrical inflexibility of existing metric learning approaches, we propose to build object and relation embeddings in separate object space and relation spaces rather than in a common space. Afterwards, we learn embeddings by firstly projecting vertices from object space to corresponding relation space and then calculate the proximity between projected vertices. To overcome the heavy skewness of the link distribution w.r.t relations and avoid "over-sampling'' or "under-sampling'' for each relation, we propose a novel loss-aware adaptive sampling approach for the model optimization. Extensive experiments have been conducted on a large-scale HIN dataset, and the experimental results show superiority of our proposed PME model in terms of prediction accuracy and scalability.

With the rapid rise of various e-commerce and social network platforms, users are generating large amounts of heterogeneous behavior data, such as purchasehistory, adding-to-favorite, adding-to-cart and click activities, and this kind of user behavior data is usually binary, only reflecting a user's action or inaction (i.e., implicit feedback data). Tensor factorization is a promising means of modeling heterogeneous user behaviors by distinguishing different behavior types. However, ambiguity arises in the interpretation of the unobserved user behavior records that mix both real negative examples and potential positive examples. Existing tensor factorization models either ignore unobserved examples or treat all of them as negative examples, leading to either poor prediction performance or huge computation cost. In addition, the distribution of positive examples w.r.t. behavior types is heavily skewed. Existing tensor factorization models would bias towards the type of behaviors with a large number of positive examples. In this paper, we propose a scalable probabilistic tensor factorization model (SPTF) for heterogeneous behavior data and develop a novel negative sampling technique to optimize SPTF by leveraging both observed and unobserved examples with much lower computational costs and higher modeling accuracy. To overcome the issue of the heavy skewness of the behavior data distribution, we propose a novel adaptive ranking-based positive sampling approach to speed up the model convergence and improve the prediction accuracy for sparse behavior types. Our proposed model optimization techniques enable SPTF to be scalable to large-scale behavior datasets. Extensive experiments have been conducted on a large-scale e-commerce dataset, and the experimental results show the superiority of our proposed SPTF model in terms of prediction accuracy and scalability.