The answer proposed by the researchers is a framework called SCLS, short for shapelet-based soft contrastive learning for multivariate time series clustering. Published online in the journal Knowledge and Information Systems, the method combines two powerful ideas from machine learning, discriminative subsequences known as shapelets and a gentler form of contrastive learning, into a four-stage pipeline that avoids the noise and uncertainty that plague earlier approaches. In experiments spanning dozens of real-world datasets, the authors report that SCLS achieved the highest performance ranking compared with state-of-the-art clustering methods.

To appreciate why this matters, it helps to understand what shapelets are and why they have become a cornerstone of time series analysis. A shapelet is a short, distinctive subsequence that captures the essence of a pattern, such as the characteristic spike in an electrocardiogram that signals a particular cardiac event or the telltale wobble in a sensor reading that precedes a machine failure. Since shapelets were introduced as a primitive for data mining in 2009, researchers have used them for classification and clustering because they are inherently interpretable: a human can look at a shapelet and see exactly which fragment of the signal drove the decision. That transparency is precious in domains like medicine and industrial monitoring, where a bare accuracy number is not enough.

Contrastive learning, meanwhile, has become one of the dominant paradigms for learning representations without labels. The idea is to teach a neural network to pull similar examples together in an embedding space while pushing dissimilar ones apart. In time series work, this is usually done through data augmentation: the same series is distorted in two different ways, for example by jittering, scaling, or cropping, and the network is trained to recognize that both distorted views came from the same source. The problem, as Wang and Yang point out, is that augmentation introduces noise and uncertainty of its own. A badly chosen distortion can destroy the very pattern that defines a class, and the augmented views may no longer resemble anything in the real data. Worse, in shapelet-based methods that lean on augmentation, the extracted shapelets can drift away from true subsequences of the original signals, eroding both interpretability and clustering quality.

SCLS sidesteps this difficulty by working directly with the original sequences rather than their distorted copies. The framework unfolds in four carefully sequenced stages. In the first, an attention mechanism fuses multiple feature components drawn from the original series. Attention, the same mechanism that powers modern language models, allows the network to weigh different parts of the signal according to their relevance, which reduces uncertainty and helps extract more representative shapelets. Rather than treating every time point and every channel as equally informative, the model learns where the discriminative structure lives.

The second stage mines multi-scale shapelets using a perceptually important points selection method based on information gain. Perceptually important points are the salient peaks, valleys, and inflection points of a curve, the skeleton of a signal that survives even when the details are smoothed away. By selecting these anchor points and measuring how much each candidate subsequence contributes to distinguishing between groups, quantified through information gain, the method can discover shapelets at multiple lengths and granularities. This multi-scale view matters because the discriminative fingerprint of a time series may be a brief transient in one dataset and a long, slow trend in another.

Third, the framework employs a shapelet encoder enhanced with a pseudo-label clustering mechanism. Pseudo-labeling is a well-known strategy in semi-supervised learning in which a model’s own provisional cluster assignments are treated as soft training signals. Here, the encoder embeds the mined shapelets into structure-aware representations, meaning the embedding preserves the relationships among shapelets rather than treating them as isolated vectors. These structure-aware embeddings then serve as the substrate for the final stage of learning.

That final stage is the soft contrastive learning strategy that gives the method its name and its distinctive character. Instead of the hard binary logic of conventional contrastive learning, where two samples are either a positive pair to be attracted or a negative pair to be repelled, soft contrastive learning assigns graded, probabilistic relationships between samples. The hierarchical strategy introduced in SCLS jointly optimizes the shapelet representation space at two levels: the temporal level, where fragments within a series are compared, and the sample level, where whole series are compared with one another. The result is a representation space whose geometry is explicitly shaped for clustering analysis, with coherent groups emerging naturally rather than being forced by rigid pairwise constraints.

The authors evaluated the framework through extensive experiments on dozens of real-world datasets, measuring clustering quality against a battery of state-of-the-art competitors. According to the published results, SCLS attained the highest performance ranking among the methods tested, suggesting that the combination of augmentation-free shapelet extraction and hierarchical soft contrastive optimization translates into a genuine advantage rather than a theoretical curiosity. The study draws on a rich lineage of prior work, from the original shapelet primitive through shapelet transformers presented at the 2024 KDD conference, multiview unsupervised shapelet learning, and recent soft contrastive approaches for time series presented at ICLR, positioning SCLS as a synthesis that resolves the specific weaknesses of each ingredient when used alone.

The practical implications reach well beyond the benchmark suite. Clustering multivariate time series underpins customer segmentation in dynamic markets, electricity consumption analysis, fault diagnosis in industrial equipment, and the discovery of patterns in online popularity dynamics, all areas represented in the study’s bibliography. Because the shapelets at the heart of SCLS remain anchored to true subsequences of the original data, practitioners gain not only clusters but also an explanation of what distinguishes them, a feature that matters whenever algorithmic decisions must be audited or acted upon by domain experts. The code supporting the findings is available from the corresponding author upon reasonable request, and the research was supported by the Guangdong Basic and Applied Basic Research Foundation and the National Natural Science Foundation of China. As sensors multiply and the volume of unlabeled temporal data grows, methods like SCLS point toward a future in which machines can find the hidden rhythms of the world without needing humans to label every beat first.

Subject of Research: Shapelet-based soft contrastive learning for multivariate time series clustering

Article Title: SCLS: Shapelet-based soft contrastive learning for multivariate time series clustering

Article References: SCLS: Shapelet-based soft contrastive learning for multivariate time series clustering. (n.d.). https://doi.org/10.1007/s10115-026-02902-2

Image Credits: AI Generated

DOI: 10.1007/s10115-026-02902-2

Keywords: multivariate time series, clustering, shapelets, contrastive learning, attention mechanism, pseudo-labeling, information gain, representation learning, data mining, unsupervised learning, feature fusion, Knowledge and Information Systems

The framework, called CADEE, short for a comprehensive online active ensemble learning framework, is described in a paper published in the journal Knowledge and Information Systems. Its central premise is that existing methods usually address only fragments of the problem: some tackle binary imbalance, others assume fully supervised streams with every label available, and many implicitly assume that class proportions remain relatively stable. In real online environments, the authors argue, class priors and decision boundaries can evolve together, and the majority or minority role of a given class may itself change over time. A class that was rare last month may become dominant next month, and a classifier that treats class roles as fixed will silently degrade as the stream moves beneath it.

Architecturally, CADEE is a unified online learning loop that stitches together six cooperating components: an online ensemble classifier, an ADWIN-based drift detector, a prediction register, an incremental trainer, a label sliding window, and a sample sliding window. ADWIN, or adaptive windowing, is a well-established technique for detecting changes in the distribution of a stream by maintaining windows of recent statistics and cutting them when the data suggests a shift. The prediction register tracks what the ensemble has predicted, the incremental trainer continuously updates base learners as new information arrives, and the two sliding windows manage the recent labeled and unlabeled history that the rest of the machinery draws upon. The result is a system in which drift detection, model updating, sample selection, and ensemble fusion are not isolated stages but tightly coupled feedback processes.

The first of the framework’s three core mechanisms is a class-aware dynamic performance calibration scheme for evaluating base classifiers. Instead of judging each member of the ensemble by a single aggregate accuracy figure, which tends to be dominated by majority classes, the calibration mechanism scores classifiers using class-level performance, prediction uncertainty, confidence, and complementary diversity among members. This matters because in imbalanced settings a classifier can look impressive overall while being nearly useless on the minority classes that often carry the greatest practical value, such as fraudulent transactions or rare fault conditions. By weighting class-level behavior and rewarding members that contribute complementary information, the fusion process reduces the dominance of majority classes when the ensemble combines its votes into a final prediction.

The second mechanism governs the size and diversity of the ensemble itself. Rather than fixing the number of base classifiers in advance, CADEE adjusts ensemble capacity according to drift severity and member complementarity. When the drift detector signals an abrupt change, the framework can expand or restructure the ensemble to restore predictive power quickly; during stable periods, it avoids unnecessary expansion that would waste computation and risk overfitting stale patterns. This drift-adaptive sizing reflects a broader principle in streaming machine learning: the amount of model capacity a system needs is not constant but should track the volatility of the environment. A rigid ensemble is either too small to absorb a sudden shift or too large and cumbersome to remain nimble when the stream settles down.

The third mechanism addresses the labeling bottleneck through a multi-factor adaptive hard-example sampling and mixing enhancement strategy. Under a limited label budget, the framework selects the most informative samples to send for annotation, prioritizing boundary cases that sit near decision frontiers and minority-related examples that would otherwise be drowned out by abundant majority data. Selected samples then feed a quality-controlled, same-class Mixup procedure, a data augmentation technique that blends examples within a class to generate synthetic training points. These augmented samples are used for incremental training, effectively squeezing more learning signal out of every expensive human label. The same-class constraint is important, because naive mixing across classes in imbalanced settings can blur the very boundaries the system is trying to sharpen.

To evaluate the framework, the team ran experiments on fifteen synthetic multi-class imbalanced data streams with different drift patterns and five real-world data streams, comparing CADEE against several state-of-the-art methods. Performance was measured with Accuracy, Kappa, G-Mean, and Recall, along with an average ranking across metrics. G-Mean, in particular, is a standard yardstick for imbalanced learning because it captures performance across all classes rather than letting majority accuracy mask minority failure. Across these benchmarks, CADEE achieved competitive or superior results relative to the compared methods, and the authors report that the framework improves label utilization, drift adaptation, and minority class recognition in non-stationary multi-class imbalanced streams.

The significance of this work lies less in any single algorithmic trick than in its insistence on treating the streaming imbalance problem as a whole. Prior research, much of it cited in the paper, has advanced individual pieces of the puzzle: adaptive random forests for evolving streams, continuous oversampling techniques such as C-SMOTE, dynamic weighted majority schemes, drift detectors tailored to imbalanced data, and active learning strategies for evolving streams. Each contribution typically optimizes one axis while holding the others fixed. CADEE’s contribution is an integration layer in which drift detection triggers ensemble restructuring, ensemble calibration protects minority classes during fusion, and active sampling concentrates scarce labels where they matter most, all within a single online loop that never assumes the stream will hold still.

The practical implications extend across the domains where streaming classification already operates. Fraud detection systems face adversaries who constantly change tactics, making concept drift a structural feature rather than an occasional nuisance. Industrial monitoring must catch rare fault signatures buried under oceans of normal-operation readings, and the definition of normal itself shifts with seasons, product lines, and aging equipment. Traffic prediction, credit risk evaluation, and smart-city sensing all combine skewed class distributions with evolving conditions and expensive ground truth. In each case, a framework that spends its labeling budget on genuinely informative examples and adapts its model capacity to the volatility of the stream could translate directly into better decisions at lower annotation cost.

The research, supported by the National Natural Science Foundation of China, the Natural Science Foundation of Ningxia, and the Central Universities Foundation of North Minzu University, arrives as the field of online machine learning grapples with a widening gap between laboratory benchmarks and production realities. Most published classifiers still assume static datasets, fixed class distributions, and abundant labels, assumptions that dissolve the moment a model is deployed against a live feed. Frameworks like CADEE point toward a different design philosophy: learning systems that treat change as the default, scarcity as a budget to be optimized, and imbalance as a moving target rather than a fixed property of the data. As more of the world’s decisions are delegated to models consuming unbounded streams, that philosophy may prove less like an academic refinement and more like a prerequisite for keeping artificial intelligence honest in a world that refuses to sit still.

Subject of Research: Online ensemble learning for multi-class imbalanced data streams with concept drift

Article Title: A comprehensive online active ensemble learning framework for multi-class imbalanced data streams with concept drift

Article References: Han, M., Xue, Y., Li, Y., Ma, C., Ding, J., & Li, J. (2026). A comprehensive online active ensemble learning framework for multi-class imbalanced data streams with concept drift. Knowledge and Information Systems, 68(1), Article 268. https://doi.org/10.1007/s10115-026-02888-x

Image Credits: AI Generated

DOI: 10.1007/s10115-026-02888-x

Keywords: machine learning, data streams, concept drift, class imbalance, ensemble learning, active learning, online learning, ADWIN, Mixup, minority class recognition, streaming classification, Knowledge and Information Systems

In a paper published in Knowledge and Information Systems, a team led by Tianyi Ma and Yanfang Ye of the University of Notre Dame, together with collaborators at the University of Connecticut and Amazon GenAI, introduces BHyGNN+, a self-supervised framework for learning representations of heterophilic hypergraphs, structures in which a single relationship, called a hyperedge, can link any number of entities that may have little or nothing in common. The work extends the group’s earlier supervised model, BHyGNN, and removes its most restrictive requirement: the need for labeled training data.

The heterophily problem is easy to illustrate. Consider a shopping dataset in which each hyperedge is a shopping cart. A single cart routinely contains products from wildly different categories, such as diapers, a phone charger, and a novel, so the items joined by that hyperedge are semantically dissimilar by design. Political datasets behave similarly: a bill co-sponsored by legislators spans party lines, so nodes connected through the same hyperedge often belong to different classes. When a neural network averages information across such dissimilar neighbors, it blurs the very distinctions that downstream tasks, like classifying a product or predicting a legislator’s party, depend on. The researchers found that on heterophilic benchmarks, even a simple multilayer perceptron that ignores network structure entirely can outperform several sophisticated hypergraph neural networks, a striking sign that conventional message passing can actively hurt in these settings.

The earlier BHyGNN model tackled this by making propagation selective. Rather than forcing every node to exchange information with every hyperedge it touches, the model learns, for each node-hyperedge pair, whether the node should broadcast its features into the hyperedge or receive information back from it. This decision is made by a Variational Broadcast Autoencoder Network that samples discrete broadcast and receive actions through a Gumbel-Softmax relaxation, and the resulting representations are refined by an incorporation transformer with multi-head attention. Trained end to end, the model worked well, but its propagation actions were guided by downstream class labels, which are precisely the resource that is scarce, expensive, or entirely absent in many practical applications, from emerging illicit drug trafficking networks to newly formed e-commerce catalogs.

BHyGNN+ replaces that label dependence with a contrastive self-supervised objective built on an elegant structural idea: hypergraph duality. Every hypergraph has a dual in which the roles of nodes and hyperedges are swapped. Each original hyperedge becomes a node in the dual, and each original node becomes a hyperedge connecting the dual nodes it belonged to. Mathematically, this amounts to transposing the incidence matrix, and it is a lossless operation. The authors prove that the dual preserves all task-relevant information, since the transform is its own inverse, and that the normalized walk operators of a hypergraph and its dual share the same nonzero eigenvalues. In spectral terms, the two views are isospectral: they encode identical nontrivial structure while exposing complementary, node-centric versus hyperedge-centric, pathways through the data.

The training procedure capitalizes on this complementarity. The framework applies four stochastic augmentations, namely node attribute masking, hyperedge perturbation that only removes members to avoid injecting noisy connections, hyperedge dropping, and node dropping, to generate corrupted views of both the original hypergraph and its dual. Each augmented view is passed through the shared hypergraph encoder, and a readout function pools node and hyperedge embeddings into a single global representation. The contrastive loss then maximizes the cosine similarity between the representation of an augmented view and that of its corresponding augmented dual. Crucially, this formulation needs no negative samples at all. Most existing hypergraph contrastive methods, such as TriCL and HyperGCL, rely on negative pairs to prevent representation collapse, but constructing high-quality negatives in large hypergraphs is difficult and computationally costly. By contrasting a structure against its own dual, BHyGNN+ sidesteps the problem entirely, using only positive pairs.

The authors also supply a theoretical argument for why duality is especially well suited to heterophilic data. They show that two hyperedges sharing even a single node, which become neighbors in the dual, have provably higher expected similarity in their class composition than random hyperedge pairs, with a strictly positive contribution arising from the shared structure alone. In a heterophilic hypergraph, where members of one hyperedge span many classes, this means the dual view reorganizes apparently incoherent node-level structure into locally coherent hyperedge-level neighborhoods. Because the global readout aggregates over all of these dual neighbors, the coherence propagates into the contrastive signal, giving the encoder a stable learning signal even when node-level homophily is absent. The bound is tightest precisely when shared nodes carry maximally diverse labels, which is exactly the heterophilic regime where other methods struggle most.

The empirical evaluation is unusually broad, spanning eleven datasets and thirteen baselines. The heterophilic benchmarks include Senate, Congress, and House, where nodes are legislators labeled by party affiliation, and Walmart, where nodes are co-purchased products; the homophilic set covers co-authorship networks such as Cora-CA and DBLP, co-citation networks including Cora, PubMed, and Citeseer, and a Twitter hypergraph for classifying roles in illicit drug trafficking networks, plus a synthetic four-class heterophilic hypergraph generated from a contextual stochastic block model. Across these benchmarks, BHyGNN+ consistently outperformed both supervised and self-supervised state-of-the-art methods, including ED-HNN, SheafHGNN, TriCL, and HypeBoy, despite never seeing a label during pretraining. Paired t-tests with Bonferroni correction confirmed that the improvements over most baselines are statistically significant, with adjusted p-values near zero on the heterophilic datasets, and the advantage was most pronounced against structure-ignoring MLPs and the generative method HypeBoy.

The framework’s advantages widen as labels become scarcer. Under a split in which only ten percent of nodes are used for training, BHyGNN+ showed a substantial improvement over its supervised predecessor BHyGNN, which struggles to learn sensible propagation actions from limited supervision. In controlled experiments on synthetic hypergraphs with homophily scores ranging from 0.4 to 0.8, all methods improved as homophily increased, but BHyGNN+ achieved the best results in the most heterophilic settings, beating the strongest baseline, TriCL, by roughly four percentage points under both moderate and high feature noise. Sensitivity analyses showed stable performance across hidden dimensions from 64 to 1024, with an augmentation ratio of 0.2 proving optimal, since heavier perturbation injects too much noise. Diagnostic plots of the embedding space ruled out representation collapse: training loss never reached zero, embedding norms remained stable, and the effective rank of the embedding matrix stayed high, notably higher for heterophilic datasets, suggesting the model automatically allocates richer representational capacity to harder structures.

The implications reach well beyond benchmark tables. Hypergraphs arise wherever group interactions matter, including biochemical networks, transaction records, legislative activity, and online communities, and in most of these domains, ground-truth labels are rare or lag reality. A method that extracts usable representations from raw structure alone, without negatives and without annotations, lowers the barrier to applying higher-order network learning in exactly those settings. The authors note open questions that remain, including extending the framework to hyperedge-level and graph-level tasks, designing augmentations tailored specifically to heterophilic structure, and deepening the theory of why duality works so well. For now, though, the message is clear: when a network looks incoherent from one angle, its mirror image may hold the pattern.

Subject of Research: Self-supervised representation learning on heterophilic hypergraphs using hypergraph duality

Article Title: Bhygnn+: unsupervised representation learning for heterophilic hypergraphs

Article References: Ma, T., Qian, Y., Wang, Z., Zhang, Z., Zhang, C., & Ye, Y. (2026). Bhygnn+: unsupervised representation learning for heterophilic hypergraphs. Knowledge and Information Systems, 68(1), Article 265. https://doi.org/10.1007/s10115-026-02834-x

Image Credits: AI Generated

DOI: 10.1007/s10115-026-02834-x

Keywords: hypergraph neural networks, self-supervised learning, contrastive learning, heterophily, hypergraph duality, representation learning, graph neural networks, unsupervised learning, node classification, higher-order networks, machine learning, Knowledge and Information Systems

The problem the researchers tackle is familiar to anyone whose phone has suggested a restaurant or a gym. Location-based social services generate enormous streams of check-in data, and turning those streams into accurate next-destination predictions has become a vibrant research area. Deep learning models have steadily improved performance by learning users’ interests and preferences, but the Chongqing team identified two persistent weaknesses in existing approaches. First, many methods built on recurrent neural networks (RNNs) process visits one after another and therefore overlook relationships between a user’s preferences for non-consecutive POI visits. A person might visit a coffee shop every Monday and a bookstore every other Saturday, but a sequential model that only sees immediate neighbors in the sequence can miss those long-range connections, leaving it unable to correctly understand the motivations behind user behavior.

The second weakness concerns short-term interests. Existing methods for analyzing what a user is doing right now, the authors argue, lack an in-depth exploration of both the overall structure and the key details of recent behavior. They fail to effectively combine a global perspective with an analysis of local critical points, the decisive moments that drive what happens next. This limitation produces an inaccurate understanding of users’ short-term interests, fails to capture dynamic changes and key driving factors comprehensively, and ultimately damages the accuracy and adaptability of the model. In practical terms, a recommender that cannot see both the forest and the trees will suggest the wrong place at the wrong time.

STFDN addresses these issues with a two-pronged architecture. The first prong is a residual block-enhanced attention architecture designed to capture the global view of both long-term and short-term user preferences. Residual blocks, a technique popularized in deep computer vision, allow information to bypass layers of processing so that early signals are not degraded as the network deepens. Combined with attention mechanisms, which let the model weigh the importance of different past visits when forming its prediction, this architecture directly tackles the issue of non-consecutive POI preferences. A visit from three weeks ago can exert just as much influence on today’s recommendation as the one from an hour ago, provided the attention mechanism learns that it matters.

The second, and more novel, prong moves the analysis into the frequency domain. The researchers designed a Fre-sequence module and a Fre-temporal module to identify dependencies between what they call energy concentration points, which they describe as analogous to dominant frequencies in signal processing. In ordinary language, these are the salient periodic patterns in a user’s behavior: the weekly coffee ritual, the monthly shopping trip, the after-work gym session. By transforming sequences of visits from the time domain, where events follow one another, into the frequency domain, where periodicities stand out as peaks of concentrated energy, the modules can spot these rhythms and model the dependencies between them. This enables an in-depth exploration of users’ short-term interests in the frequency domain, pairing the global structural view with a fine-grained reading of the critical points that actually drive movement.

The idea of analyzing sequential data through its frequency content has been gaining traction in adjacent fields. The authors draw on recent work showing that frequency-domain multilayer perceptrons can be more effective learners in time-series forecasting, suggesting that human mobility, like stock prices or weather, carries structure that is easier to read once the noise of raw chronology is stripped away. Applying that insight to POI recommendation is a distinctive move, because mobility data is not merely a time series. Each visit carries spatial coordinates, temporal context and semantic content, and a useful model must fuse all three. STFDN’s spatiotemporal framing, reflected in its name, is intended to do exactly that, layering frequency-domain analysis on top of representations that respect where and when each check-in occurred.

To test the approach, the team ran extensive experiments on two benchmark datasets, comparing STFDN against a crowded field of competitors that includes recurrent models, attention-based architectures and spatio-temporal gated networks. The reported result is straightforward: the model outperforms other state-of-the-art algorithms. The authors’ contribution statement indicates that Huang led conceptualization, methodology, software, visualization, validation, data curation and the original draft, while Zhang supervised the work and contributed formal analysis, review and editing, with He, Li and Li handling validation, resources, investigation and formal analysis. The work was supported by the National Natural Science Foundation of China and the Natural Science Foundation Project of Chongqing.

The lineage of this research stretches back more than a decade. Early POI recommenders relied on matrix factorization enriched with geographical and social influence, exploiting the observation that people tend to visit places near places they already like. Successive generations added sequential modeling, starting with factorizing personalized Markov chains and moving through attentional recurrent networks such as DeepMove, contextual attention architectures, and temporal and multi-level context attention models. More recently, spatio-temporal attention networks and transformer-style recommenders have mined relationships between visited locations directly. Each generation has chipped away at the same core question: how much of a person’s future is explained by their last stop, and how much by the deeper pattern of their life?

STFDN’s answer is that both matter, but in different ways, and that a single model can hold both views simultaneously. The residual-enhanced attention branch preserves the long arcs of preference that stretch across weeks, while the frequency modules compress recent activity into its most meaningful periodic components and let the model reason about them explicitly. This division of labor is what the authors say was missing from prior short-term interest analyses, which tended to treat recent history as either an undifferentiated blob or a fine-grained but myopic list. The frequency-domain lens offers a middle path, keeping the details that repeat and discarding the incidental noise.

The implications extend beyond restaurant suggestions. Accurate next-location prediction underpins urban planning, traffic management, epidemic modeling and personalized travel services, and any method that better captures the periodic structure of human movement could feed those applications. The field also continues to broaden its toolkit, with neighboring work by some of the same authors exploring latent diffusion models for social recommendation, smooth diffusion models for multimodal recommendation, and hierarchy-aware diffusion with knowledge-enhanced contrastive learning. For now, STFDN stands as a demonstration that sometimes the best way to understand where people are going is to stop watching their footsteps and start listening to the rhythm underneath them. The study, published as volume 68, article 262 of Knowledge and Information Systems, was received in April 2025, revised in June 2026 and published on 22 September 2026.

Subject of Research: Spatiotemporal frequency-domain deep learning for next point-of-interest recommendation

Article Title: Spatiotemporal frequency-domain network for next POI recommendation

Article References: Spatiotemporal frequency-domain network for next POI recommendation. (n.d.). https://doi.org/10.1007/s10115-026-02883-2

Image Credits: AI Generated

DOI: 10.1007/s10115-026-02883-2

Keywords: POI recommendation, frequency domain, recommender systems, deep learning, attention mechanism, user preferences, human mobility, spatiotemporal modeling, recurrent neural networks, short-term interests, check-in data, Knowledge and Information Systems