While user preferences are important to cross-domain recommendation (CDR), existing methods primarily discover preferences under specific, yet possibly redundant, item features. To this end, we first propose a novel Preference Prototype-Aware (PPA) learning method to quantitatively learn user preferences while minimizing disturbances from the source domain. It introduces a mix-encoder and a proto-decoder. On the one hand, the mix-encoder learns better general representations of interacted items and captures the intrinsic relationships between items across different domains. On the other hand, the proto-decoder implements a learnable prototype matching mechanism to quantitatively perceive user preferences, avoiding disturbances caused by item features from the source domain. Moreover, through experiments on PPA, we observe another two issues that affect existing CDR methods’ performance, i.e., the semantic deficiency caused by sparse item categories and the imbalance weights caused by different user-item distributions. Thus, we further propose a LoRA-based extractor and a domain cross-attention module to alleviate the two issues, respectively. The PPA incorporating with new extractor and attention module is called PPA++. Extensive experiments show that PPA++ outperforms the other state-of-the-art counterparts in four different CDR scenarios.

Recent advancements in Large Language Models (LLMs) have significantly extended context windows, igniting discussions about the necessity of Retrieval-Augmented Generation (RAG). U-NIAH, a unified Needle-in-a-Haystack (NIAH) framework, systematically evaluates LLMs and RAG methods in controlled long-context settings. It extends beyond traditional NIAH by incorporating more practical and complex scenarios like multi-needle, long-needle, and needle-in-needle configurations and leveraging the synthetic dataset to mitigate LLM biases. The experiments aim to address three research questions in long-context scenarios: (1) performance tradeoffs between LLMs and RAG, (2) error patterns in RAG, and (3) RAG’s limitations in complex settings. Results show that smaller LLMs benefit more from RAG. In all settings, RAG achieves a win rate of 82.58% over direct answers. Additionally, it is found that retrieval noise and chunk ordering degrade RAG performance, and we further summarized typical error patterns, including omissions due to noise, hallucinations under high noise critical conditions, and self-doubt behaviors, as well as how these phenomena vary with context length. Finally, in some challenging scenarios, experiments show that deep reasoning models are more easily affected by distractors. These findings highlight the complementary roles of RAG and LLMs and offer actionable insights for optimizing deployment strategies ( https://github.com/Tongji-KGLLM/U-NIAH ).

Retrieval Augmented Generation (RAG) has emerged as a promising solution to address hallucination issues in Large Language Models (LLMs). However, the integration of multiple retrieval sources, while potentially more informative, introduces new challenges that can paradoxically exacerbate hallucination problems. These challenges manifest primarily in two aspects: the sparse distribution of multi-source data that hinders the capture of logical relationships and the inherent inconsistencies among different sources that lead to information conflicts. To address these challenges, we propose MultiRAG, a novel framework designed to mitigate hallucination in multi-source retrieval-augmented generation through knowledge-guided approaches. Our framework introduces two key innovations: (1) a knowledge construction module that employs multi-source line graphs to efficiently aggregate logical relationships across different knowledge sources, effectively addressing the sparse data distribution issue; and (2) a sophisticated retrieval module that implements a multi-level confidence calculation mechanism, performing both graph-level and node-level assessments to identify and eliminate unreliable information nodes, thereby reducing hallucinations caused by inter-source inconsistencies. Extensive experiments on four multi-domain query datasets and two multi-hop QA datasets demonstrate that MultiRAG significantly enhances the reliability and efficiency of knowledge retrieval in complex multi-source scenarios. Our code is available in https://github.com/wuwenlong123/MultiRAG.

A well-designed recommender system can accurately learn the embeddings of users and items, reflecting the unique preferences of users. Traditional recommendation techniques usually focus on modeling the singular type of behaviors between users and items. However, in many practical recommendation scenarios (e.g., social media, e-commerce), there exist multi-typed interactive behaviors in user–item relationships, such as click, tag-as-favorite, and purchase in online shopping platforms. Thus, how to make full use of multi-behavior information for recommendation is of great importance to the existing system, which presents challenges in two aspects that need to be explored: (1) Utilizing users’ personalized preferences to capture multi-behavioral dependencies; (2) Dealing with the insufficient recommendation caused by sparse supervision signal for target behavior. In this work, we propose the Knowledge Enhancement Multi-Behavior Contrastive Learning (KMCL) framework , including two Contrastive Learning tasks and three functional modules to tackle the above challenges, respectively. In particular, we design the multi-behavior learning module to extract users’ personalized behavior information for user-embedding enhancement and utilize knowledge graph in the knowledge enhancement module to derive more robust knowledge-aware representations for items. In addition, in the optimization stage, we also model the coarse-grained commonalities and the fine-grained differences between multi-behavior of users to further improve the recommendation effect and propose a joint training paradigm to enhance the learning effect of KMCLR in the joint learning module. Besides, we also considered how to make full use of temporal signals to enhance the effectiveness of multi-behavior recommendations in scenarios with time information and designed a novel encoder to address this issue. Extensive experiments and ablation tests on the three real-world datasets indicate that our KMCLR outperforms various state-of-the-art recommendation methods and verify the effectiveness of our method.

Identifying disinformation from online social media is crucial for maintaining a credible cyberspace. Although features from the content and propagation topology are widely exploited by existing studies to distinguish disinformation from normal ones, they are becoming less effective as content can be intentionally written to mislead readers and topological features are difficult to be extracted due to the high variance and diversity of reposting trees. Moreover, related works mainly focus on modeling the complete information propagation event, ignoring the staged evolution patterns along with propagation, which may also degrade the detection performance. In this paper, we conceive and implement a novel framework called DMPS for identifying disinformation, which Dynamically Models diverse topological structures of reposting trees as well as the textual content streams across different Propagation Stages. In particular, DMPS learns expressive representations of the structural features via meta-trees and extracts sequential features of the content for intra-stage modeling, then it captures temporal dependencies for inter-stage modeling. The whole framework is optimized in a binary classification manner. Experiments based on multilingual social media datasets validate the effectiveness and superiority of DMPS over state-of-the-art models. We believe that this study can provide insights for crisis management in response to disinformation in social network campaigns.

Cross-domain recommendation (CDR) aims to suggest items from new domains that align with potential user preferences, based on their historical interactions. Existing methods primarily focus on acquiring item representations by discovering user preferences under specific, yet possibly redundant, item features. However, user preferences may be more strongly associated with interacted items at higher semantic levels, rather than specific item features. Consequently, this item feature-focused recommendation approach can easily become suboptimal or even obsolete when conducting CDR with disturbances of these redundant features. In this paper, we propose a novel Preference Prototype-Aware (PPA) learning method to quantitatively learn user preferences while minimizing disturbances from the source domain. The PPA framework consists of two complementary components: a mix-encoder and a preference prototype-aware decoder, forming an end-to-end unified framework suitable for various real-world scenarios. The mix-encoder employs a mix-network to learn better general representations of interacted items and capture the intrinsic relationships between items across different domains. The preference prototype-aware decoder implements a learnable prototype matching mechanism to quantitatively perceive user preferences, which can accurately capture user preferences at a higher semantic level. This decoder can also avoid disturbances caused by item features from the source domain. The experimental results on public benchmark datasets in different scenarios demonstrate the superiority of the proposed PPA learning method compared to state-of-the-art counterparts. PPA excels not only in providing accurate recommendations but also in offering reliable preference prototypes. Our code is available at https://github.com/zyx-nuaa/PPA-for-CDR.

Existing knowledge graph query approaches, whether traditional textual query languages or visual query languages, have steep learning curves that are unfriendly for non-expert users. This demonstration presents a Visual Query approach based on Full-Text search for knowledge graphs, called VQFT, which simplifies the process of querying knowledge graphs for users. Inspired by full-text search techniques, VQFT aims to combine the user-friendliness of visual query with the intuitiveness of full-text search , enabling users to query knowledge graphs as straightforward as using a search engine. Faceted full-text indexes, visual query constructor , and an interactive user interface are designed to achieve this goal. User tests and surveys have demonstrated that VQFT is more user-friendly and easier to learn than existing methods, which simplifies the construction of knowledge graph queries for non-expert users.

We study the problem of processing continuous$k$nearest neighbor (C$k$NN) queries over moving objects on road networks, which is an essential operation in a variety of applications. We are particularly concerned with scenarios where the object densities in different parts of the road network evolve over time as the objects move. Existing methods on C$k$NN query processing are ill-suited for such scenarios as they utilize index structures with fixed granularities and are thus unable to keep up with the evolving object densities. In this paper, we directly address this problem and propose an object density aware index structure called ODIN that is an elastic tree built on a hierarchical partitioning of the road network. It is equipped with the unique capability of dynamically folding/unfolding its nodes, thereby adapting to varying object densities. We further present the ODIN-KNN-Init and ODIN-KNN-Inc algorithms for the initial identification of the$k$NNs and the incremental update of query result as objects move. Thorough experiments on both real and synthetic datasets confirm the superiority of our proposal over several baseline methods.

Knowledge graphs (KGs) are commonly used as side information to enhance collaborative signals and improve recommendation quality. In the context of knowledge-aware recommendation (KGR), graph neural networks (GNNs) have emerged as promising solutions for modeling factual and semantic information in KGs. However, the long-tail distribution of entities leads to sparsity in supervision signals, which weakens the quality of item representation when utilizing KG enhancement. Additionally, the binary relation representation of KGs simplifies hyper-relational facts, making it challenging to model complex real-world information. Furthermore, the over-smoothing phenomenon results in indistinguishable representations and information loss.

Using trajectories of moving objects and performing contact event query during disease transmission is an effective method of prevention and control. Existing contact query processing algorithms only consider single-source (one-to-one) contact event and thus can not discover multi-source (n-to-one) contact events. In this paper, we propose efficient multi-source contact event query processing methods that are capable of querying multi-source contact events. The definition of multi-source contact events is first formulated. Then, a baseline multi-source contact event query processing algorithm is presented, which adopts the idea of sliding window-based sequential scanning. To improve the query efficiency, the 2-dimensional bitmap filter and the anchor time point scanning are designed and used in the optimized query processing algorithm. Comprehensive experiments on real-world data demonstrate that the proposed algorithms can find more potential contact events and have good performance in the manner of query time cost.

A well-designed recommender system can accurately capture the attributes of users and items, reflecting the unique preferences of individuals. Traditional recommendation techniques usually focus on modeling the singular type of behaviors between users and items. However, in many practical recommendation scenarios (e.g., social media, e-commerce), there exist multi-typed interactive behaviors in user-item relationships, such as click, tag-as-favorite, and purchase in online shopping platforms. Thus, how to make full use of multi-behavior information for recommendation is of great importance to the existing system, which presents challenges in two aspects that need to be explored: (1) Utilizing users' personalized preferences to capture multi-behavioral dependencies; (2) Dealing with the insufficient recommendation caused by sparse supervision signal for target behavior. In this work, we propose a Knowledge Enhancement Multi-Behavior Contrastive Learning Recommendation (KMCLR) framework, including two Contrastive Learning tasks and three functional modules to tackle the above challenges, respectively. In particular, we design the multi-behavior learning module to extract users' personalized behavior information for user-embedding enhancement, and utilize knowledge graph in the knowledge enhancement module to derive more robust knowledge-aware representations for items. In addition, in the optimization stage, we model the coarse-grained commonalities and the fine-grained differences between multi-behavior of users to further improve the recommendation effect. Extensive experiments and ablation tests on the three real-world datasets indicate our KMCLR outperforms various state-of-the-art recommendation methods and verify the effectiveness of our method.

Abstract Patient similarity search is an essential task in healthcare. Recent studies adopted electronic health records (EHRs) to learn patient representations for measuring the clinical similarities. These methods outperformed traditional methods, by capturing more information from various sources consisting of multi-modal EHRs, external knowledge and correlations among medical concepts. They often concerned certain type of data without taking full advantage of various information. We propose a graph representation learning framework, denoted by One-Size-Fits-Three ( OSFT ), that takes into account fusion-attention, neighbor-attention and global-attention from three types of information. Extensive experiments are conducted on two real datasets of MIMIC-III and MIMIC-IV, and the results verified the effectiveness and generality of our framework. When compared with baselines on patient similarity search, our framework achieved good effectiveness and comparative efficiency. The results provide new insights about whether the use of various information can better measure the patient similarity. The source codes are available at https://github.com/emmali808/ADDS/tree/master/EHRDeepHelper .

Abstract Advanced knowledge engineering (KE), represented by knowledge graph (KG), drives the development of various fields and engineering technologies and provides various knowledge fusion and knowledge empowerment interfaces. At the same time, advanced system engineering (SE) takes model-based system engineering (MBSE) as the core to realize formal modeling and process analysis of the whole system. The two complement each other and are the key technologies for the transition from 2.0 to 3.0 in the era of artificial intelligence and the transition from perceptual intelligence to cognitive intelligence. This survey summarizes an advanced information fusion system, from model-driven to knowledge-enabled. Firstly, the concept, representative methods, key technologies and application fields of model-driven system engineering are introduced. Then, it introduces the concept of knowledge-driven knowledge engineering, summarizes the architecture and construction methods of advanced knowledge engineering and summarizes the application fields. Finally, the combination of advanced information fusion systems, development opportunities and challenges are discussed.

With the popularity of mobile devices equipped with positioning devices, it is convenient to obtain enormous amounts of trajectory data. The development promotes the study of extracting moving patterns from trajectory data of moving objects. One such pattern is the convoy, which refers to a group of objects moving together for a period of time. The existing convoy mining algorithms have a large time cost because they adopt a density-based clustering algorithm over global objects. In this paper, we propose an efficient convoy mining algorithm (ECMA) that adopts the divide-and-conquer methodology. A block-based partition model (BP-Model) is designed to divide objects into multiple maximized connected nonempty block areas (MOBAs). The convoy mining problem is then solved by processing each MOBA sequentially, which significantly reduces the time cost of convoy mining. In the experiments, we evaluate the performance of our algorithm on real-world datasets. The results show that the ECMA is more efficient than existing convoy mining algorithms.

Sequential recommendation systems seek to learn users' preferences to predict their next actions based on the items engaged recently. Static behavior of users requires a long time to form, but short-term interactions with items usually meet some actual needs in reality and are more variable. RNN-based models are always constrained by the strong order assumption and are hard to model the complex and changeable data flexibly. Most of the CNN-based models are limited to the fixed convolutional kernel. All these methods are suboptimal when modeling the dynamics of item-to-item transitions. It is difficult to describe the items with complex relations and extract the fine-grained user preferences from the interaction sequence. To address these issues, we propose a knowledge-aware sequential recommender with the attention-enhanced dynamic convolutional network (KAeDCN). Our model combines the dynamic convolutional network with attention mechanisms to capture changing dependencies in the sequence. Meanwhile, we enhance the representations of items with Knowledge Graph (KG) information through an information fusion module to capture the fine-grained user preferences. The experiments on four public datasets demonstrate that KAeDCN outperforms most of the state-of-the-art sequential recommenders. Furthermore, experimental results also prove that KAeDCN can enhance the representations of items effectively and improve the extractability of sequential dependencies.

We are pleased to present a special issue of Data Science and Engineering (DSE), which contains a collection of six extended papers from the APWeb-WAIM 2020 conference.We also include a regular submission paper in this issueAPWeb-WAIM conferences focus on research, development, and applications in relation to Web information management, including a wide range of topics, such as text analysis, graph data processing, social networks, recommender systems, information retrieval, data streams, knowledge graph, data mining and application, query processing, machine learning, database and Web applications, big data, and blockchain.

The problem of route planning on road network is essential to many Location-Based Services (LBSs). Road networks are dynamic in the sense that the weights of the edges in the corresponding graph constantly change over time, representing evolving traffic conditions. Thus, a practical route planning strategy is required to supply the continuous route optimization considering the historic, current, and future traffic condition. However, few existing works comprehensively take into account these various traffic conditions during the route planning. Moreover, the LBSs usually suffer from extensive concurrent route planning requests in rush hours, which imposes a pressing need to handle numerous queries in parallel for reducing the response time of each query. However, this issue is also not involved by most existing solutions. We therefore investigate a parallel traffic condition driven route planning model on a cluster of processors. To embed the future traffic condition into the route planning, we employ a GCN model to periodically predict the travel costs of roads within a specified time period, which facilitates the robustness of the route planning model against the varying traffic condition. To reduce the response time, a Dual-Level Path (DLP) index is proposed to support a parallel route planning algorithm with the filter-and-refine principle. The bottom level of DLP partitions the entire graph into different subgraphs, and the top level is a skeleton graph that consists of all border vertices in all subgraphs. The filter step identifies a global directional path for a given query based on the skeleton graph. In the refine step, the overall route planning for this query is decomposed into multiple sub-optimizations in the subgraphs passed through by the directional path. Since the subgraphs are independently maintained by different processors, the sub-optimizations of extensive queries can be operated in parallel. Finally, extensive evaluations are conducted to confirm the effectiveness and superiority of the proposal.

Resume block classification is the most significant step in resume information extraction. However, the existing algorithms applied to resume block classification are all the general text classification algorithms, which failed to consider the contextual order of each block within a resume. In order to improve the performance of resume block classification, we propose in this paper a block-level bidirectional recurrent neural network model that makes full use of the contextual order relationship among different resume blocks. The experimental results show that the average F1-score value of our model on three 1,400 real resume datasets is 6% to 9% higher than the existing methods.