Recent advances in explainable recommendation have explored the integration of language models to analyze natural language rationales for user–item interactions. Despite their potential, existing methods often rely on ID-based representations that obscure semantic meaning and impose structural constraints on language models, thereby limiting their applicability in open-ended scenarios. These challenges are intensified by the complex nature of real-world interactions, where diverse user intents are entangled and collaborative signals rarely align with linguistic semantics. To overcome these limitations, we propose BEAT, a unified and transferable framework that tokenizes user and item behaviors into discrete, interpretable sequences. We construct a behavior vocabulary via a vector-quantized autoencoding process that disentangles macro-level interests and micro-level intentions from graph-based representations. We then introduce multi-level semantic supervision to bridge the gap between behavioral signals and language space. A semantic alignment regularization mechanism is designed to embed behavior tokens directly into the input space of frozen language models. Experiments on three public datasets show that BEAT improves zero-shot recommendation performance while generating coherent and informative explanations. Further analysis demonstrates that our behavior tokens capture fine-grained semantics and offer a plug-and-play interface for integrating complex behavior patterns into large language models.

Mobile signaling data has been used to discover comprehensive and fine-grained patterns of individual travel activities. However, mobile signaling data often exhibits notable data quality issues caused by systematic factors (e.g., weather, construction, congestion) or individual factors (e.g., low battery, poor reception). Improving the quality of signaling data is a crucial yet challenging task due to irregular spatiotemporal intervals and complex inter-correlations among base stations. In this paper, we formalize the augmentation of signaling data as a base station location reconstruction task. We propose a location-aware transformer structure named SigFormer, which employs self-supervised learning to reconstruct the location information of missing base stations based on the sampled signaling sequence. Specifically, we first design a Continuous Signaling Encoder to model irregularly sampled signaling sequences and encode interval information generated by base station transitions. Then, we learn the Base Station Embedding to describe implicit features of base stations and design a Neighbor Region Encoder to incorporate geographic information as an auxiliary for base station representations. Finally, through an attention-based encoder-decoder framework, we aggregate location information and base station features, employing sequence learning to capture spatiotemporal dependencies and reconstruct base station locations. Experiment results on real-world datasets indicate that our method outperforms existing approaches for location reconstruction. The proposed method originates from practical demands in telecom systems, addressing the challenge of missing and abnormal base station locations by modeling spatiotemporal transition patterns in signaling data. Our approach supports various tasks in practical applications, including imputing missing base station locations and correcting anomalous locations, effectively improving the quality of signaling data.

Multi-task architecture learning has achieved significant success by learning optimal sharing architectures for different tasks. However, previous works to learn branched architectures for different tasks can sometimes lead to unsatisfying multi-task performance, as not all detailed branches are relevant to a specific task. Task-relevant architectures can be sparse, including only partial channels or layers in the entire architecture (i.e., a sub-network). In addition, most previous works rely on a heuristic architecture selection procedure that could not support continuous architecture optimization. To this end, in this paper, we propose dual-mask , a progressively sparse multi-task architecture learning method. Starting with a task-free architecture, it identifies the informative features along two-level, channels and layers, for each task, while suppressing conflicting or noisy parts in a differentiable manner, so that better task-specific sub-networks are captured. Specifically, the channel and layer selection modules produce respective hybrid binary and real value masks, designed to pick salient channels and layers for each task, respectively. To jointly optimize masks with model parameters, we propose an importance-guided relaxation method for solving the stochastic binary optimization problem , after which the interference or noise parts can be pruned by masks. Additionally, a progressive training strategy with continuation is provided that gradually sparsity the task-specific sub-networks. Experiments show that dual-mask achieves superior performance than SOTA multi-task methods.

Information diffusion prediction, aimed at estimating future interacting users for a given content, is crucial for various applications on online social platforms. Recently, methods based on dynamic graph learning have achieved superior performance. However, these methods often face scalability issues due to their full-neighbor aggregation, which requires loading the whole diffusion graph, making them impractical for large graphs. While improving model scalability through sampling is an immediate approach, it is challenging on the diffusion graph due to various user dependencies (i.e., the temporal and structural correlations of user–item interactions). To address this problem, we propose a new model named ASDIP, which performs adaptive sampling on the diffusion graph. Specifically, ASDIP employs multiple sampling strategies to extract walks from the diffusion graph, each identifying a representative user dependency by sampling walks that satisfy a specific temporal constraint. Next, the walks sampled by different strategies are first mapped into distinct strategy-specific user representations and then merged into a unified user representation, adaptively fusing the information obtained from different strategies. Finally, a cascade representation learning module is proposed to generate cascade representations based on user representations and interaction timestamps. Experimental results validate the effectiveness and scalability of ASDIP.

Dynamic graph learning has attracted much attention in recent years due to the fact that most of the real-world graphs are dynamic and evolutionary.As a result, many dynamic learning methods have been proposed to cope with the changes of node states over time.Among these studies, a critical issue is how to update the representations of nodes when new temporal events are observed.In this paper, we provide a novel memory structure -Memory Map (MemMap) for this problem.MemMap is an adaptive and evolutionary latent memory space, where each cell corresponds to an evolving "topic" of the dynamic graph.Moreover, the representation of a node is generated from its semantically correlated memory cells, rather than linked neighbors of the node.We have conducted experiments on real-world datasets and compared our method with the SOTA ones.It can be concluded that: 1) By constructing an adaptive and evolving memory structure during the dynamic learning process, our method can capture the dynamic graph changes, and the learned MemMap is actually a compact evolving structure organized according to the latent "topics" of the graph nodes.2) Our research suggests that it is a more effective and efficient way to generate node representations from a latent semantic space (like MemMap in our method) than from directly connected neighbors (like most of the previous graph learning methods).The reason is that the number of memory cells in latent space could be much smaller than the number of nodes in a real-world graph, and the representation learning process could well balance the global and local message passing by leveraging the semantic similarity of graph nodes via the correlated memory cells.

Temporal link prediction, aiming at predicting future interactions among entities based on historical interactions, is crucial for a series of real-world applications. Although previous methods have demonstrated the importance of relative encodings for effective temporal link prediction, computational efficiency remains a major concern in constructing these encodings. Moreover, existing relative encodings are usually constructed based on structural connectivity, where temporal information is seldom considered. To address the aforementioned issues, we first analyze existing relative encodings and unify them as a function of temporal walk matrices. This unification establishes a connection between relative encodings and temporal walk matrices, providing a more principled way for analyzing and designing relative encodings. Based on this analysis, we propose a new temporal graph neural network called TPNet, which introduces a temporal walk matrix that incorporates the time decay effect to simultaneously consider both temporal and structural information. Moreover, TPNet designs a random feature propagation mechanism with theoretical guarantees to implicitly maintain the temporal walk matrices, which improves the computation and storage efficiency. Experimental results on 13 benchmark datasets verify the effectiveness and efficiency of TPNet, where TPNet outperforms other baselines on most datasets and achieves a maximum speedup of $33.3 \times$ compared to the SOTA baseline.

Travel time estimation (TTE) is a fundamental and challenging problem for navigation and travel planning. Though many efforts have been devoted to this task, most of the previous research has focused on extracting useful features of the routes to improve the estimation accuracy. In our opinion, the key issue of TTE is how to handle the rich spatiotemporal information underlying a route and how to model the multi-faceted factors that affect travel time. Along this line, we propose a multi-faceted route representation learning framework that divides a route into three sequences: a trajectory sequence consists of GPS coordinates to describe spatial information, an attribute sequence to encode the features of each road segment, and a semantic sequence consists of the IDs of road segments to capture the context information of routes. Then, we design a sequential learning module and transformer encoder to get the representations of three sequences for each route respectively. Finally, we fuse the multi-faceted route representations together, and provide a self-supervised learning module to improve the generalization of final representation. Experiments on two real-world datasets demonstrate that our method could provide more accurate travel time estimation than baselines, and all the multi-faceted route representations contribute to the improvement of estimation accuracy.

Origin-Destination demand prediction is a fundamental and important task in the urban transportation system. It is more challenging and complex than region demand prediction since it needs to predict traffic demand for each pair of regions rather than a single region, which means$N^{2}$time series need to be predicted given$N$stations. Most existing works are mainly proposed for the region (or station) demand prediction. On the other hand, previous Origin-Destination demand prediction methods only follow a single discrete-time setting while the input data are continuous-time OD orders, which means these methods have not sufficiently leveraged the rich information for demand prediction. To solve these challenges, we propose a novel framework consisting of both continuous-time and discrete-time representation learning modules for Origin-Destination demand prediction. Firstly, we construct memorable representations of all nodes and design a continuous-time learning module to update the nodes’ representations once a time-stamped OD transaction is observed. Then, a discrete-time representation learning module is proposed to generate discrete-time messages containing information across a fixed time interval from a macro perspective. Next, a co-updater module is designed to fuse messages from both continuous-time and discrete-time channels into node memory. Last, a graph attention module is developed, which generates final node embeddings using updated node memory and predicts the forthcoming OD demand matrix based on them. The experimental results on real-world datasets show that our method leads to significant and consistent improvements compared to other methods.

Given a sequence of sets, where each set contains an arbitrary number of elements, temporal sets prediction aims to predict which elements will appear in the subsequent set. Existing methods for temporal sets prediction are developed on sophisticated components (e.g., recurrent neural networks, attention or gating mechanisms, and graph neural networks), which inevitably increase the model complexity due to more trainable parameters and higher computational costs. Moreover, the involved nonlinear activation may contribute little or even degrade the performance. In this paper, we present a succinct architecture that is solely built on the Simplified Fully Connected Networks (SFCNs) for temporal sets prediction to bring both effectiveness and efficiency together. In particular, given a user's sequence of sets, we employ SFCNs to derive representations of the user by learning inter-set temporal dependencies, intra-set element relationships, and intra-embedding channel correlations. Two families of general functions are introduced to preserve the permutation-invariant property of each set and the permutation-equivariant property of elements in each set. Moreover, we design a user representations adaptive fusing module to aggregate user representations according to each element for improving the prediction performance. Experiments on four benchmarks show the superiority of our approach over the state-of-the-art under both transductive and inductive settings. We also theoretically and empirically demonstrate that our model has lower space and time complexity than baselines. Codes and datasets are available at https://github.com/yule-BUAA/SFCNTSP.

Many deep spatio-temporal learning methods have been proposed for crowd flow modeling in recent years. However, most of them focus on designing a spatial and temporal convolution mechanism to aggregate information from nearby nodes and historical observations for a pre-defined prediction task. Different from the existing research, this paper aims to provide a generic and dynamic representation learning method for crowd flow modeling. The main idea of our method is to maintain a continuous-time representation for each node, and update the representations of all nodes continuously according to the streaming observed data. Along this line, a particular encoder-decoder architecture is proposed, where the encoder converts the newly happened transactions into a timestamped message, and then the representations of related nodes are updated according to the generated message. The role of the decoder is to guide the representation learning process by reconstructing the observed transactions based on the most recent node representations. Moreover, a number of virtual nodes are added to discover macro-level spatial patterns and also share the representations among spatially-interacted stations. Experiments have been conducted on two real-world datasets for four popular prediction tasks in crowd flow modeling. The result demonstrates that our method could achieve better prediction performance for all the tasks than baseline methods.

The development of learning analytics technology has created the necessary conditions for the implementation of large-scale personalized education. By taking advantage of the current advancements available, we can adopt a deep integration of “artificial intelligence + education”, take educational big data as the research object, aim at achieving precise teaching, and use cognitive diagnosis as a means to construct an intelligent guidance model. The model will conform to a learner's cognitive patterns and curriculum characteristics to meet his personalized learning needs under different knowledge states. Firstly, use knowledge map and abstract syntax trees to extract the characteristics of teaching objectives from questions and standard programing codes. Secondly, Use “target characteristics - learning characteristics - learning sequence - learning effect” cognitive diagnosis model to assess student achievement in learning. Finally, according to the correlation between knowledge points, the initial learning path consisting of all relevant knowledge points is identified from a knowledge map. And the most optimal learning path is selected based on the importance of knowledge points and student's learning situation. There are three innovation points in this paper. First, the traditional method which only focuses on discovering the one-dimensional knowledge features implicated in the questions, is extended to construct a knowledge-ability multidimensional feature matrix. Secondly, it optimized static cognitive diagnosis into dynamic cognitive arbitrariness, which has a modeling capability of dynamic temporal sequence. Thirdly, it regarded the correlation between knowledge points, and the importance of knowledge points as the heuristic conditions for constructing a learning path.

Information propagation on social networks could be modeled as cascades, and many efforts have been made to predict the future popularity of cascades. However, most of the existing research treats a cascade as an individual sequence. Actually, the cascades might be correlated with each other due to the shared users or similar topics. Moreover, the preferences of users and semantics of a cascade are usually continuously evolving over time. In this paper, we propose a continuous-time graph learning method for cascade popularity prediction, which first connects different cascades via a universal sequence of user-cascade and user-user interactions and then chronologically learns on the sequence by maintaining the dynamic states of users and cascades. Specifically, for each interaction, we present an evolution learning module to continuously update the dynamic states of the related users and cascade based on their currently encoded messages and previous dynamic states. We also devise a cascade representation learning component to embed the temporal information and structural information carried by the cascade. Experiments on real-world datasets demonstrate the superiority and rationality of our approach.

Forecasting traffic flow is an important task in urban areas, and a large number of methods have been proposed for traffic flow prediction. However, most of the existing methods follow a general technical route to aggregate historical information spatially and temporally. In this paper, we propose a different approach for traffic flow prediction. Our major motivation is to more effectively incorporate various intrinsic patterns in real-world traffic flows, such as fixed spatial distributions, topological correlations, and temporal periodicity. Along this line, we propose a novel autoencoder-based traffic flow prediction method, named Spatio-Temporal AutoEncoder (ST-AE). The core of our method is an autoencoder specially designed to learn the intrinsic patterns from traffic flow data, and encode the current traffic flow information into a low-dimensional representation. The prediction is made by simply projecting the current hidden states to the future hidden states, and then reconstructing the future traffic flows with the trained autoencoder. We have conducted extensive experiments on four real-world data sets. Our method outperforms existing methods in several settings, particularly for long-term traffic flow prediction.

Graph Neural Networks (GNNs) have been widely applied in the semi-supervised node classification task, where a key point lies in how to sufficiently leverage the limited but valuable label information. Most of the classical GNNs solely use the known labels for computing the classification loss at the output. In recent years, several methods have been designed to additionally utilize the labels at the input. One part of the methods augment the node features via concatenating or adding them with the one-hot encodings of labels, while other methods optimize the graph structure by assuming neighboring nodes tend to have the same label. To bring into full play the rich information of labels, in this article we present a label-enhanced learning framework for GNNs, which first models each label as a virtual center for intra-class nodes and then jointly learns the representations of both nodes and labels. Our approach could not only smooth the representations of nodes belonging to the same class, but also explicitly encode the label semantics into the learning process of GNNs. Moreover, a training node selection technique is provided to eliminate the potential label leakage issue and guarantee the model generalization ability. Finally, an adaptive self-training strategy is proposed to iteratively enlarge the training set with more reliable pseudo labels and distinguish the importance of each pseudo-labeled node during the model training process. Experimental results on both real-world and synthetic datasets demonstrate our approach can not only consistently outperform the state-of-the-arts, but also effectively smooth the representations of intra-class nodes.

A hard landing occurs when an aircraft or spacecraft hits the ground with a greater vertical speed and force than in a normal landing, which can cause serious damage to the aircraft and even put passengers in great danger. Predicting the hard landing ahead is valuable, however, it has not been fully investigated. Existing studies mainly apply statistical machine learning algorithms with feature engineering on small-scale data sets. Such methods are primarily dependent on constructing features by experts. In addition, since hard landing samples are difficult to collect, existing research only use a small-scale training sets, which limits the capacity of models. In this paper, we explore a novel autoregressive pre-training approach for hard landing prediction using its flight parameters before touchdown provided by quick access recorder (QAR). QAR is an airborne flight data recorder that records more than 1000 flight parameters throughout the whole flight phase. Large amount of landing data from QAR, which can be considered as multivariate time series, were processed and converted to symbolic representations. Each token represents one landing status in a landing time series. An Aircraft Landing Model (ALM) is pre-trained on these landing token sequences in an autoregressive way that predicts the next landing status according to the previous landing status. The pre-trained ALM can learn the transition patterns between landing status in a normal landing and automatically extract useful features to characterize a landing process. Finally, the pre-trained ALM model is fine-tuned on hard landing training set to predict hard landing. Experimental results show that our approach significantly improved F-Score of hard landing prediction by 14% compared to other methods.

One of the most fundamental tasks in the socially aware network (SAN) paradigm is to explore the attributes and behavior of users, which helps to design more suitable and efficient protocols. Particularly, detection of shilling attackers by mining users’ behavior is a frequently discussed topic in many social scenes like recommender systems based on collaborative filtering. As the performances of collaborative filtering are entirely based on ratings provided by users, they are vulnerable to shilling attacks which perform injection of biased profiles into rating databases to alter the systems. Current shilling attack detection methods detect spam users through artificially designed features, which are neither robust nor efficient enough. This paper illustrates a novel convolutional neural network-based method named CNN-SAD, which applies transformed network structure to exploit deep-level features from users rating profiles. Since the achieved deep-level features elaborate users rating more precisely than artificially designed features, CNN-SAD can detect shilling attacks more efficiently. According to the experimental results, the proposed method is capable of detecting the vast majority of obfuscated attacks precisely and outperforms other state-of-the-art algorithms, which contributes to applications and security in SAN.

Traffic speed is one of the most essential parameters representing traffic conditions in intelligent traffic system (ITS). In recent years, there have been several approaches estimating traffic speed based on cellular network signaling data. However, the accuracy of these approaches is unsatisfactory because they have a poor performance in filtering out noisy data and minimizing deviations of traffic speed values' trend in adjacent time intervals. In this paper, a new approach is proposed to solve the two problems above. The approach filters out noisy data according to educated judgment, and adopts a modified Kalman filter algorithm to minimize the deviations. The performance study on real data sets of Beijing shows that the accuracy of the proposed approach is higher when compared with existing two notable estimation approaches. Further the approach will contribute to developing intelligent navigation systems and pursuing artificial intelligence applications.

Call detail records (CDRs) containing mass position information allow us to reveal characteristics about the city dynamics and human behaviors, which are crucial for policy decisions such as urban planning and transportation engineering. Being able to identify the trajectory and significant places is of prime importance. In this paper, we aim to extract trajectory from anonymized call detail records and adopt two-step clustering to obtain significant places from multi-day data. We propose a new method for mining trajectory by identifying users' stop and move state based on location gradient, which can be applied to users with low communication frequency. We analyze the feature of real CDR data and propose novel methods for noise handling. Home Time and Work Time are extracted from statistics of users' mobility pattern to recognize their significant places including home and work of a single day. Utilizing the characteristic of cyclical mobility, we conduct a cluster analysis to identify users' significant places which are not limited to one home or one work based on multi-day data. We run four experiments to show the robustness and stability of our method. During both typical stop and move period, our method performs better than state-of-art method.

A set of distributed continual range query requests, each defining a geographical region of interest, needs to be periodically reevaluated to provide up to date answers. Processing these continual queries efficiently and incrementally becomes important for location based services and applications. In this paper, we propose an efficient incremental method for continuous range query characterized by mobility of objects which follow paths in an underlying spatial road network. We notice that both queries and moving objects can be attached to the road link for updating of query answers. By using Grid R∗-tree which indexing spatial road network data, query requests and moving objects register themselves to corresponding road links according to query areas and moving object locations on the network. Also we analyzed the impacts to query answers caused by geometry relation of road link and query area and state of moving objects. Then we proposed an efficient update algorithm and corresponding memory data structures based on spatial and state classification which formed a safe region to avoid unnecessary updates. Finally a comprehensive experimental evaluation using real data has been conducted to demonstrate the efficiency and effectiveness of our algorithm.

Nowadays Float Car Data (FCD) is playing an important role in real-time traffic information systems. However, traffic signal control in urban road network will cause random delay on float cars, and this kind of delay will result in considerable fluctuation of travel time. Thus, the accuracy of FCD system is seriously affected. In this paper, float car refining models are proposed to calculate the stopped-time delay by means of low-sampling-rate FCD. And then, the classification of controlled delay and non-controlled delay is performed in order to remove traffic signal control's affection, and to obtain the data which can truly reflect the traffic flow characteristics. The contrast experiments indicate that the accuracy of the FCD system has achieved significant improvement after applying the new processing model.