Cross-Domain Recommendation (CDR) aims to alleviate data sparsity in the target domain by incorporating knowledge from external domains. Existing approaches typically rely on overlapping users between the source and target domains as a bridge for knowledge transfer. However, in practice, user information across domains is often unavailable due to privacy protection, platform isolation, and data sharing restrictions, rendering most methods ineffective. In this article, we propose the D2TCDR, a two-stage generative CDR framework to address this critical limitation. By modeling the domain-level distribution that captures user preferences shared across domains, we extract transferable knowledge and guide its transfer through a generative process, reducing reliance on overlapping users and alleviating data sparsity in the target domain. D2TCDR first proposes a domain disentanglement module to extract the domain-invariant representations, capturing shared preferences across domains by eliminating domain-specific interference. Subsequently, a guided diffusion model is designed to model the domain-level distribution of these domain-invariant representations. By injecting target-domain signals into the guided diffusion model, we further steer the learned distribution toward the target domain, achieving knowledge transfer without relying on overlapping users. Extensive experiments on multiple cross-domain datasets show the superior performance of D2TCDR, validating its recommendation capabilities in complex transfer scenarios. Code is available at: https://github.com/Red-Week/D2TCDR .

Cross-domain recommendation (CDR) has gained significant attention for its ability to address data sparsity issue. However, most existing CDR methods focus primarily on improving recommendation accuracy while largely overlooking fairness considerations, which can lead to biased outcomes and unfair treatment of different user groups. To solve this critical problem, we investigate whether fairness can be transferred from the source domain to the target domain. Our analysis suggests that fairness can be effectively transferred if the fairness of the source domain is ensured and the distributions of the source and target domains are well aligned. Based on this, we propose the FairCDR, a novel framework that can achieve the knowledge transfer of fairness and user preferences simultaneously. FairCDR owns two phases: single-domain fairness guarantee and inter-domain distribution alignment. In the first phase, we employ an adversarial learning-based recommender (ALR) to disentangle user preferences from sensitive attributes in the source domain. In the second phase, we introduce a new mutual learning-based diffusion model (MLDiff), which engages in mutual learning with ALR to progressively align the distributions of the source and target domains. This improves ALR's adaptability to distribution shifts, ultimately ensuring fairness and recommendation performance in the target domain. Extensive experiments on multiple real-world cross-domain datasets demonstrate that FairCDR surpasses existing strong baselines in both fairness and recommendation quality.

We introduce TabFormer, a framework that normalizes diverse semi-structured tables into relational data via large language models to facilitate various table retrieval and reasoning tasks. Our approach employs a chain-of-thought methodology, transforming one or multiple tables through a sequence of soft operations. Compared to existing operators that are sensitive and brittle to human-induced artifacts in real-world tables, soft operators are designed with greater flexibility to accommodate diverse formatting variations.

Large language models (LLMs) achieve superior performance in generative tasks. However, due to the natural gap between language model generation and structured information extraction in three dimensions: task type, output format, and modeling granularity, they often fall short in structured information extraction, a crucial capability for effective data utilization on the web. In this paper, we define the generation process of the language model as the controllable state transition, aligning the generation and extraction processes to ensure the integrity of the output structure and adapt to the goals of the information extraction task. Furthermore, we propose the Structure2Text decider to help the language model understand the fine-grained extraction information, which converts the structured output into natural language and makes state decisions, thereby focusing on the task-specific information kernels, and alleviating language model hallucinations and incorrect content generation. We conduct extensive experiments and detailed analyses on myriad information extraction tasks, including named entity recognition, relation extraction, and event argument extraction. Our method not only achieves significant performance improvements but also considerably enhances the model's capability to generate precise and relevant content, making the extracted content easy to parse.

Graph-level out-of-distribution (OOD) detection, which attempts to identify OOD graphs originated from an unknown distribution, is a vital building block for safety-critical applications in Web and society. Current approaches concentrate on how to learn better graph representations, but fail to provide any statistically guarantee on detection results, therefore impeding their deployments in the scenario where detection errors would result in serious consequences. To overcome this critical issue, we propose the Conformal Graph-level Out-of-distribution Detection (CGOD), extending the theory of conformal prediction to graph-level OOD detection with a rigorous control over the false positive rate. In CGOD, we develop a new aggregated non-conformity score function based on the proposed adaptive data augmentation. Through the guidance from two designed metrics, i.e., score consistency and representation diversity, our augmentation strategy can generate multiple non-conformity scores, and aggregating these generated non-conformity scores together is robust to the misleading information. Meanwhile, our score function can perceive the subsequent process of conformal inference, enabling the aggregated non-conformity score to be adaptive to different input graphs and deriving a more accurate score estimation. We conduct experiments on multiple real-world datasets with different empirical settings. Extensive results and model analyses demonstrate the superior performance of our approach over several competitive baselines.

Multimodal recommendation, which utilizes rich multimodal information to learn user preferences, has attracted significant attention. Most works focus on designing powerful encoders for extracting multimodal features, and simply aggregate the learned features together to make prediction. Consequently, they have a limited capacity to learn the inter-modality knowledge including the modality-shared and modality-unique knowledge. In fact, learning the modality-shared knowledge enables us to align cross-modality data for fusing heterogeneous modality features. Learning the modality-unique knowledge is equally important when recommendation tasks only involve a small amount of shared features and the necessary information is contained within specific modality. In this article, we propose Contrastive Modality-Disentangled Learning (CMDL) to overcome this critical limitation. CMDL exactly captures the inter-modality knowledge by achieving modality disentanglement. Specifically, CMDL first disentangles the initial representation into the modality-invariant and modality-specific representations. Afterwards, CMDL introduces a novel manner of contrastive learning to approximate the MI upper bounds for achieving disentanglement regularization. Building upon the proposed regularization, CMDL encourages the modality-invariant and modality-specific representations to capture the modality-shared and modality-unique knowledge respectively and to be statistically independent to each other. Empirically, extensive experiments are conducted on benchmark datasets, demonstrating the superior performance of CMDL compared with strong multimodal recommenders.

In today's digital age, accessing information across language barriers poses a significant challenge, with conventional search systems often struggling to interpret and retrieve multilingual content accurately. Addressing this issue, our study introduces a novel integration of applying Large Language Models (LLMs) as Cross-lingual Readers in information retrieval systems, specifically targeting the complexities of cross-lingual information retrieval (CLIR). We present an innovative approach: Activation Steered Multilingual Retrieval (ASMR) that employs "steering activations''-a method to adjust and direct the LLM's focus-enhancing its ability to understand user queries and generate accurate, language-coherent responses. ASMR adeptly combines a Multilingual Dense Passage Retrieval (mDPR) system with an LLM, overcoming the limitations of traditional search engines in handling diverse linguistic inputs. This approach is particularly effective in managing the nuances and intricacies inherent in various languages. Rigorous testing on established benchmarks such as XOR-TyDi QA, and MKQA demonstrates that ASMR not only meets but surpasses existing standards in CLIR, achieving state-of-the-art performance. The results of our research hold significant implications for understanding the inherent features of how LLMs understand and generate natural languages, offering an attempt towards more inclusive, effective, and linguistically diverse information access on a global scale.

Answering complex logical queries over knowledge graphs (KGs) is a fundamental yet challenging task. Recently, query representation has been a mainstream approach to complex logical reasoning, making the target answer and query closer in the embedding space. However, there are still two limitations. First, prior methods model the query as a fixed vector, but ignore the uncertainty of relations on KGs. In fact, different relations may contain different semantic distributions. Second, traditional representation frameworks fail to capture the joint distribution of queries and answers, which can be learned by generative models that have the potential to produce more coherent answers. To alleviate these limitations, we propose a novel generative model, named DiffCLR, which exploits the diffusion model for complex logical reasoning to approximate query distributions. Specifically, we first devise a query transformation to convert logical queries into input sequences by dynamically constructing contextual subgraphs. Then, we integrate them into the diffusion model to execute a multi-step generative process, and a structure-enhanced self-attention is further designed for incorporating the structural features embodied in KGs. Experimental results on two benchmark datasets show our model effectively outperforms state-of-the-art methods, particularly in multi-hop chain queries with significant improvement.

In the contemporary digital landscape, search engines play an invaluable role in information access, yet they often face challenges in Cross-Lingual Information Retrieval (CLIR). Though attempts are made to improve CLIR, current methods still leave users grappling with issues such as misplaced named entities and lost cultural context when querying in non-native languages. While some advances have been made using Neural Machine Translation models and cross-lingual representation, these are not without limitations. Enter the paradigm shift brought about by Large Language Models (LLMs), which have transformed search engines from simple retrievers to generators of contextually relevant information. This paper introduces the Multilingual Information Model for Intelligent Retrieval (MIMIR). Built on the power of LLMs, MIMIR directly responds in the language of the user's query, reducing the need for post-search translations. Our model's architecture encompasses a dual-module system: a retriever for searching multilingual documents and a responder for crafting answers in the user's desired language. Through a unique unified training framework, with the retriever serving as a reward model supervising the responder, and in turn, the responder producing synthetic data to refine the retriever's proficiency, MIMIR's retriever and responder iteratively enhance each other. Performance evaluations via CLEF and MKQA benchmarks reveal MIMIR's superiority over existing models, effectively addressing traditional CLIR challenges.

Recommender systems have been widely adopted in various online personal e-commerce applications for improving user experience. A long-standing challenge in recommender systems is how to provide accurate recommendation to users in cold-start situations where only a few user-item interactions can be observed. Recently, meta learning methods provide a promising solution, and most of them follow a way of parameter initialization where predictions can be fast adapted via multiple gradient descent steps. While these meta-learning recommenders promote model performance, how to derive a fundamental paradigm that enables both flexible approximations of complex user interaction distributions and effective task adaptations of global knowledge still remains a critical yet under-explored problem. To this end, we present the Flow-based Adaptive Neural Process (FANP), a new probabilistic meta-learning model where estimating the preference of each user is governed by an underlying stochastic process. Following an encoder-decoder generative framework, FANP is an effective few-shot function estimator that directly maps limited user interactions to a predictive distribution without complicated gradient updates. Through introducing a conditional normalization flow-based encoder, FANP can get rid of the model bias on latent variables and thereby derive more flexible variational distributions. Meanwhile, we propose a task-adaptive mechanism capturing the relevance of different tasks for improving adaptation ability of global knowledge. The learned task-specific and task-relevant representations are simultaneously exploited to generate the decoder parameters via a novel modulation-augmented hypernetwork. FANP is evaluated on both scenario-specific and user-specific cold-start recommendations on various real-world datasets. Extensive experimental results and detailed model analyses demonstrate that our model yields superior performance compared with multiple state-of-the-art meta-learning recommenders.

Data augmentation has been widely studied as it can be used to improve the generalizability of graph representation learning models. However, existing works focus only on the data augmentation on homogeneous graphs. Data augmentation for heterogeneous graphs remains under-explored. Considering that heterogeneous graphs contain different types of nodes and links, ignoring the type information and directly applying the data augmentation methods of homogeneous graphs to heterogeneous graphs will lead to suboptimal results. In this paper, we propose a novel Multi-Aspect Heterogeneous Graph Augmentation framework named MAHGA. Specifically, MAHGA consists of two core augmentation strategies: structure-level augmentation and metapath-level augmentation. Structure-level augmentation pays attention to network schema aspect and designs a relation-aware conditional variational auto-encoder that can generate synthetic features of neighbors to augment the nodes and the node types with scarce links. Metapath-level augmentation concentrates on metapath aspect, which constructs metapath reachable graphs for different metapaths and estimates the graphons of them. By sampling and mixing up based on the graphons, MAHGA yields intra-metapath and inter-metapath augmentation. Finally, we conduct extensive experiments on multiple benchmarks to validate the effectiveness of MAHGA. Experimental results demonstrate that our method improves the performances across a set of heterogeneous graph learning models and datasets.

Recommender systems which captures dynamic user interest based on time-ordered user-item interactions plays a critical role in the real-world. Although existing deep learning-based recommendation systems show good performances, these methods have two main drawbacks. Firstly, user interest is the consequence of the coaction of many factors. However, existing methods do not fully explore potential influence factors and ignore the user-item interaction formation process. The coarse-grained modeling patterns cannot accurately reflect complex user interest and leads to suboptimal recommendation results. Furthermore, these methods are implicit and largely operate in a black-box fashion. It is difficult to interpret their modeling processes and recommendation results. Secondly, recommendation datasets usually exhibit scale-free distributions and some existing recommender systems take advantage of hyperbolic space to match the data distribution. But they ignore that the operations in hyperbolic space are more complex than that in Euclidean space which further increases the difficulty of model interpretation. To tackle the above shortcomings, we propose an E xplainable H yperbolic T emporal P oint P rocess for User-Item Interaction Sequence Generation (EHTPP) . Specifically, EHTPP regards each user-item interaction as an event in hyperbolic space and employs a temporal point process framework to model the probability of event occurrence. Considering that the complexity of user interest and the interpretability of the model,EHTPP explores four potential influence factors related to user interest and uses them to explicitly guide the probability calculation in the temporal point process. In order to validate the effectiveness of EHTPP, we carry out a comprehensive evaluation of EHTPP on three datasets compared with a few competitive baselines. Experimental results demonstrate the state-of-the-art performances of EHTPP.

Graph meta-learning which is used to deal with graph few-shot learning attracts more and more research interests. Existing graph meta-learning methods mainly focus on capturing node-level relations, but they ignore task-level relations which are beneficial for improving the performance of few-shot node classification. Furthermore, contrastive learning which can learn knowledge without labeled data is suitable for few-shot scenario, but existing graph few-shot learning methods have never exploited it. To tackle above problems, in this paper, we combine conventional graph meta-learning framework with graph contrastive learning and propose a novel joint model named -${\underline T}$asklevel -${\underline R}$elations Modelling for -${\underline G}$raph ${\underline M}$eta-learning (TRGM). By constructing auxiliary contrastive pretext tasks, TRGM can fully capture the inter-task relations (task correlation and task discrepancy) and promote the primary few-shot learning. Finally, we conduct extensive experiments on six benchmark datasets to validate the effectiveness and efficiency of TRGM. Experimental results show that our model outperforms several strong baselines and achieves the new state-of-the-art.

In the fraud graph, fraudsters often interact with a large number of benign entities to hide themselves. So, there are not only the homophilic connections formed by the same label nodes (similar nodes), but also the heterophilic connections formed by the different label nodes (dissimilar nodes). However, the existing GNN-based fraud detection methods just enhance the homophily in fraud graph and use the low-pass filter to retain the commonality of node features among the neighbors, which inevitably ignore the difference among neighbor of heterophilic connections. To address this problem, we propose a Graph Neural Network-based Fraud Detector with Homophilic and Heterophilic Interactions (H2-FDetector for short). Firstly, we identify the homophilic and heterophilic connections with the supervision of labeled nodes. Next, we design a new information aggregation strategy to make the homophilic connections propagate similar information and the heterophilic connections propagate difference information. Finally, a prototype prior is introduced to guide the identification of fraudsters. Extensive experiments on two real public benchmark fraud detection tasks demonstrate that our method apparently outperforms state-of-the-art baselines.

User cold-start recommendation is a long-standing challenge for recommender systems due to the fact that only a few interactions of cold-start users can be exploited. Recent studies seek to address this challenge from the perspective of meta learning, and most of them follow a manner of parameter initialization, where the model parameters can be learned by a few steps of gradient updates. While these gradient-based meta-learning models achieve promising performances to some extent, a fundamental problem of them is how to adapt the global knowledge learned from previous tasks for the recommendations of cold-start users more effectively.

A popular choice for extractive summarization is to conceptualize it as sentence-level classification, supervised by binary labels. While the common metric ROUGE prefers to measure the text similarity, instead of the performance of classifier. For example, BERTSUMEXT, the best extractive classifier so far, only achieves a precision of 32.9% at the top 3 extracted sentences ([email protected]) on CNN/DM dataset. It is obvious that current approaches cannot model the complex relationship of sentences exactly with 0/1 targets. In this paper, we introduce DistilSum, which contains teacher mechanism and student model. Teacher mechanism produces high entropy soft targets at a high temperature. Our student model is trained with the same temperature to match these informative soft targets and tested with temperature of 1 to distill for ground-truth labels. Compared with large version of BERTSUMEXT, our experimental result on CNN/DM achieves a substantial improvement of 0.99 ROUGE-L score (text similarity) and 3.95 [email protected] score (performance of classifier). Our source code will be available on Github.

Graph neural networks (GNNs) have been successfully used to analyze non-Euclidean network data. Recently, there emerge a number of works to investigate the robustness of GNNs by adding adversarial noises into the graph topology, where gradient-based attacks are widely studied due to their inherent efficiency and high effectiveness. However, the gradient-based attacks often lead to sub-optimal results due to the discrete structure of graph data. To this end, we design a novel exploratory adversarial attack (termed as EpoAtk) to boost the gradient-based perturbations on graphs. The exploratory strategy in EpoAtk includes three phases, generation, evaluation and recombination, with the goal of sidesteping the possible misinformation that the maximal gradient provides. In experiments, EpoAtk is evaluated on benchmark datasets for the task of semi-supervised node classification in different attack settings. Experimental results demonstrate that the proposed method significantly outperforms the state-of-the-art attacks with the same attack budgets.

Entity Linking (EL) is a task for mapping mentions in text to corresponding entities in knowledge base (KB). This task usually includes candidate generation (CG) and entity disambiguation (ED) stages. Recent EL systems based on neural network models have achieved good performance, but they still face two challenges: (i) Previous studies evaluate their models without considering the differences between candidate entities. In fact, the quality (gold recall in particular) of candidate sets has an effect on the EL results. So, how to promote the quality of candidates needs more attention. (ii) In order to utilize the topical coherence among the referred entities, many graph and sequence models are proposed for collective ED. However, graph-based models treat all candidate entities equally which may introduce much noise information. On the contrary, sequence models can only observe previous referred entities, ignoring the relevance between the current mention and its subsequent entities. To address the first problem, we propose a multi-strategy based CG method to generate high recall candidate sets. For the second problem, we design a Sequential Graph Attention Network (SeqGAT) which combines the advantages of graph and sequence methods. In our model, mentions are dealt with in a sequence manner. Given the current mention, SeqGAT dynamically encodes both its previous referred entities and subsequent ones, and assign different importance to these entities. In this way, it not only makes full use of the topical consistency, but also reduce noise interference. We conduct experiments on different types of datasets and compare our method with previous EL system on the open evaluation platform. The comparison results show that our model achieves significant improvements over the state-of-the-art methods.

Entity linking is the task of aligning mentions to corresponding entities in a given knowledge base. Previous studies have highlighted the necessity for entity linking systems to capture the global coherence. However, there are two common weaknesses in previous global models. First, most of them calculate the pairwise scores between all candidate entities and select the most relevant group of entities as the final result. In this process, the consistency among wrong entities as well as that among right ones are involved, which may introduce noise data and increase the model complexity. Second, the cues of previously disambiguated entities, which could contribute to the disambiguation of the subsequent mentions, are usually ignored by previous models. To address these problems, we convert the global linking into a sequence decision problem and propose a reinforcement learning model which makes decisions from a global perspective. Our model makes full use of the previous referred entities and explores the long-term influence of current selection on subsequent decisions. We conduct experiments on different types of datasets, the results show that our model outperforms state-of-the-art systems and has better generalization performance.

As a popular heuristic to the matrix rank minimization problem, nuclear norm minimization attracts intensive research attentions. Matrix factorization based algorithms can reduce the expensive computation cost of SVD for nuclear norm minimization. However, most matrix factorization based algorithms fail to provide the theoretical guarantee for convergence caused by their non-unique factorizations. This paper proposes an efficient and accurate Linearized Grassmannian Optimization (Lingo) algorithm, which adopts matrix factorization and Grassmann manifold structure to alternatively minimize the subproblems. More specially, linearization strategy makes the auxiliary variables unnecessary and guarantees the close-form solution for low per-iteration complexity. Lingo then converts linearized objective function into a nuclear norm minimization over Grassmannian manifold, which could remedy the non-unique of solution for the low-rank matrix factorization. Extensive comparison experiments demonstrate the accuracy and efficiency of Lingo algorithm. The global convergence of Lingo is guaranteed with theoretical proof, which also verifies the effectiveness of Lingo.

Event causality is indispensable for knowledge-driven intelligent systems. In this paper, we propose a supervised method of extracting event causalities such as forest is cut down $$\rightarrow $$ forest is destroyed from web text. While relation identification using lexico-syntactic patterns (LSPs) is not novel, it is still challenging to extract the event expressions with necessary arguments from identified causality mentions. To address this issue, our method divides event-pair extraction into two phases: event boundary identification and missing argument identification. In the first phase, we propose a Naive Baysian probability method to identify the boundary of causal events, and extract the corresponding text fragments as event expressions. Secondly, we learn a multi-class decision tree (LADTree) to identify the missing argument for each incomplete event. Experimental results showed the good effectiveness of our approach on a large-scale open corpus.

In Chinese, there are many characters which are similar in shape, and this phenomenon usually induces writing errors. As one important issue in spelling automatic correction, shape similarity measurement is still a challenging problem. To address this issue, we propose a component-tree based method in this paper, which is based on the hypothesis “characters are similar if their construction and components are both similar”. Firstly, we decompose each character to a tree recursively, in which the root node is the character and the leaf nodes are atomic parts, called strokes. Then, we align any pair of trees using their minimal super-tree and calculate their similarity from bottom to up based on weighted edit distance. Finally, the cognitive prominence is used to adjust the similarity scores. In text proofreading experiments, our method achieved 97% precision and 95.6% recall, which can be applied in practical systems.

Detecting outliers from big data plays an important role in network security. Previous outlier detection algorithms are generally incapable of handling big data. In this paper we present an parallel outlier detection method for big data, based on a new parallel auto-encoder method. Specifically, we build a replicator model of the input data to obtain the representation of sample data. Then, the replicator model is used to measure the replicability of test data, where records having higher reconstruction errors are classified as outliers. Experimental results show the performance of the proposed parallel algorithm.

In this paper, we study a new problem on social network influence maximization. The problem is defined as, given a target user $w$, finding the top-k most influential nodes for the user. Different from existing influence maximization works which aim to find a small subset of nodes to maximize the spread of influence over the entire network (i.e., global optima), our problem aims to find a small subset of nodes which can maximize the influence spread to a given target user (i.e., local optima). The solution is critical for personalized services on social networks, where fully understanding of each specific user is essential. Although some global influence maximization models can be narrowed down as the solution, these methods often bias to the target node itself. To this end, in this paper we present a local influence maximization solution. We first provide a random function, with low variance guarantee, to randomly simulate the objective function of local influence maximization. Then, we present efficient algorithms with approximation guarantee. For online social network applications, we also present a scalable approximate algorithm by exploring the local cascade structure of the target user. We test the proposed algorithms on several real-world social networks. Experimental results validate the performance of the proposed algorithms.

Behavior targeting (BT) is a promising tool for online advertising. The state-of-the-art BT methods, which are mainly based on regression models, have two limitations. First, learning regression models for behavior targeting is difficult since user clicks are typically several orders of magnitude fewer than views. Second, the user interests are not fixed, but often transient and influenced by media and pop culture. In this paper, we propose to formulate behavior targeting as a classification problem. Specifically, we propose to use an SVM ensemble for behavior prediction. The challenge of using ensemble SVM for BT stems from the computational complexity (it takes 53 minutes in our experiments to predict behavior for 32 million users, which is inadequate for online application). To this end, we propose a fast ensemble SVM prediction framework, which builds an indexing structure for SVM ensemble to achieve sub-linear prediction time complexity. Experimental results on real-world large scale behavior targeting data demonstrate that the proposed method is efficient and outperforms existing linear regression based BT models.