IJCAI 2026 Papers

Real-time clustering of dynamic multi-view data streams is a critical yet challenging task in open-world applications. While several methods have been proposed to address this task, most of them extract features incrementally but fail to output instant clustering results for the current batch. In addition, they neglect semantic consistency, causing the cluster labels of identical concepts to drift unpredictably due to independent processing. To address these limitations, we propose a real-time semantic consistent incremental multi-view clustering framework. Specifically, we constructs a compact historical knowledge base via an adaptive diversity-aware selection mechanism, which guides the clustering of incoming data, enabling immediate inference without accessing the full history. Furthermore, we introduce a semantic alignment strategy based on consensus centers to ensure robust label consistency over time. Extensive experiments demonstrate the effectiveness and efficiency of our proposed method.

Multivariate Time Series Classification (MTSC) demands models that can effectively capture complex temporal patterns across multiple scales while remaining computationally efficient. However, existing approaches generally struggle to reconcile fine-grained representation learning, especially under class imbalance and real-world constraints. In this paper, we present FreSH, a Frequency-Segmented Hierarchical Multi-Expert Framework designed to address these challenges. FreSH introduces a new perspective for MTSC by enabling adaptive, multi-scale analysis of temporal signals, allowing different aspects of the data to be modeled in a complementary and coordinated manner. By combining localized specialization with holistic context modeling, FreSH achieves strong representational capacity without incurring excessive computational overhead. An adaptive fusion strategy further enhances flexibility, enabling the model to dynamically emphasize the most informative components of the input. In addition, we incorporate a more robust optimization objective that improves learning stability across varying sample difficulties and class distributions. Extensive evaluations on 30 UEA benchmark datasets and real-world vibration data demonstrate that FreSH consistently outperforms state-of-the-art methods in classification accuracy, while substantially reducing model size and efficiency. The implementation code is publicly available at https://github.com/Wangmy2120/FreSH00.

Graph Neural Networks are susceptible to label noise, in which message-passing mechanisms serve as conduits for propagating erroneous supervision. Current mitigation techniques typically recover clean labels via heuristics that lack theoretical grounding, which often leads to ineffective denoising. To tackle the issue, we propose NAEM, a latent label estimation framework that models clean labels as latent variables by integrating neighborhood agreement into the Expectation-Maximization (EM) paradigm. To overcome the posterior collapse problem in standard EM under severe noise, we design a structure-aware E-step that leverages neighborhood agreement as a structural prior. This mechanism acts as a dynamic confidence gate based on local consensus to prevent the model from overfitting to noise. Simultaneously, by explicitly modeling the noise transition matrix in the M-step, NAEM decouples noise dynamics from semantic representation learning. Extensive experiments on five benchmark datasets demonstrate that NAEM consistently outperforms SOTA methods under varying noise conditions, validating the effectiveness of our framework.

Graph self-supervised learning (SSL) typically relies on large-scale unlabeled datasets, heavily inflating computational costs. However, empirical evidence suggests that these datasets contain substantial redundancy—our analysis reveals that uniformly subsampling 50% of graphs retains over 96% of downstream performance. To exploit this redundancy, we introduce GraphSculptor for pre-training coreset construction. Unlike methods dependent on additional training-time signals or limited solely to topological statistics, GraphSculptor provides a label-free solution that constructs coresets via two complementary perspectives: intrinsic structure and contextual semantics. Concretely, structural diversity is quantified using intrinsic graph statistics, yielding a structural feature vector for each graph, while semantic diversity is captured by utilizing a pre-trained language model to encode descriptions generated via graph-to-text. GraphSculptor integrates these signals into a unified metric space and performs cluster-aware selection to preserve joint structural--semantic diversity. We further derive a theoretical bound on the loss gap between coreset and full-data pre-training, offering theoretical motivation for our selection formulation. Extensive experiments demonstrate that GraphSculptor effectively "sculpts" the dataset: a 10% coreset achieves 99.6% of full-data performance while reducing pre-training time by nearly 90%, offering a scalable solution for data-efficient graph pre-training.

Microscopic road-network weights represent fine-grained, time-varying traffic conditions obtained from individual vehicles. An example is travel speeds associated with road segments as vehicles traverse them. These weights support tasks including traffic microsimulation and vehicle routing with reliability guarantees. We study the problem of time-varying microscopic weight completion. During a time slot, the available weights typically cover only some road segments. Weight completion recovers distributions for the weights of every road segment at the current time slot. This problem involves two challenges: (i) contending with two layers of sparsity, where weights are missing at both the network layer (many road segments lack weights) and the segment layer (a segment may have insufficient weights to enable accurate distribution estimation); and (ii) achieving a weight distribution representation that is closed-form and can capture complex conditions flexibly, including heavy tails and multiple clusters. To address these challenges, we propose DiSGMM that combines sparsity-aware embeddings with spatiotemporal modeling to leverage sparse known weights alongside learned segment properties and long-range correlations for distribution estimation. DiSGMM represents distributions of microscopic weights as learnable Gaussian mixture models, providing closed-form distributions capable of capturing complex conditions flexibly. Experiments on two real-world datasets show that DiSGMM can outperform state-of-the-art methods.

Large language models (LLMs) are widely applied in various natural language processing tasks such as question answering and machine translation. However, due to the lack of labeled data and the difficulty of manual annotation for biochemical properties, the performance for molecule generation tasks is still limited, especially for tasks involving multi-properties constraints. In this work, we present a two-step framework PEIT (Property Enhanced Instruction Tuning) to improve LLMs for molecular-related tasks. In the first step, we use textual descriptions, SMILES, and biochemical properties as multimodal inputs to pre-train a model called PEIT-GEN, by aligning multi-modal representations to synthesize instruction data. In the second step, we fine-tune existing open-source LLMs with the synthesized data, the resulting PEIT-LLM can handle molecule captioning, text-based molecule generation, molecular property prediction, and our newly proposed multi-constraint molecule generation tasks. Experimental results show that our pre-trained PEIT-GEN outperforms MolT5, BioT5, MolCA and Text+Chem-T5 in molecule captioning, demonstrating modalities align well between textual descriptions, structures, and biochemical properties. Furthermore, PEIT-LLM shows promising improvements in multi-task molecule generation, demonstrating the effectiveness of the PEIT framework for various molecular tasks. The code and appendix are available at https://github.com/chenlong164/PEIT.

Capturing global context through attention is essential for reasoning over knowledge graphs, especially when relevant entities are distant or disconnected. To scale attention to large graphs, recent methods replace Softmax with kernel feature mappings, reducing computational complexity to linear in the number of nodes. While efficient, these approximations tend to produce overly smooth attention scores, which can reduce discrimination between correct triplets and hard negative samples. Moreover, they exhibit scale-dependent shifts in attention entropy, making them sensitive to changes in graph size during inductive inference. In this paper, we introduce LaGR, a novel approach for integrating global information in knowledge graph reasoning. Rather than approximating interactions among all nodes, LaGR compresses the graph into a fixed, compact set of latent summaries and applies exact self-attention within this latent space. This change yields scale-invariant attention and stable performance across diverse data settings. In addition, we propose a node-adaptive residual fusion mechanism that dynamically balances local and global information at the node level, leading to more expressive representations. Extensive experiments on both transductive and inductive benchmarks show that LaGR substantially outperforms state-of-the-art baselines, demonstrating that exact attention over latent summaries is an efficient and effective way to capture global context in knowledge graph reasoning. Our implementation is available at https://github.com/XMU-KG/LaGR.

Network Traffic Anomaly Detection (NTAD), particularly under zero-positive settings, is a critical task in cybersecurity. Existing zero-positive NTAD approaches primarily rely on reconstruction-based pipelines. Nevertheless, these methods are susceptible to an identical shortcut issue, where models indiscriminately reconstruct both normal and anomalous inputs, leading to anomaly overgeneralization. To address this limitation, we propose BiPred, the first prediction-based detection paradigm for NTAD. BiPred symmetrically divides each network traffic sample into two segments and reformulates the NTAD task as a bidirectional prediction across these two segments. Unlike reconstruction-based methods, our BiPred not only eliminates shortcut learning by design but also establishes explicit bidirectional contextual dependencies, making it more sensitive to anomalous traffic. Moreover, we develop a novel Residual Scanning Mamba block that encodes multi-view contextual information to support bidirectional prediction. A residual fusion mechanism is proposed for the multi-view scanning Mamba to suppress the accumulation of inter-view redundancy. This design prevents representation degradation and provides multi-view contextual details for prediction. Extensive experiments demonstrate the superiority of our BiPred paradigm, highlighting a new research direction for NTAD. Code is available at https://github.com/ikun0124/BiPred.

Accurate traffic flow prediction is fundamental to Intelligent Transportation Systems (ITS). However, traffic dynamics exhibit inherent multi-scale heterogeneity, where stable global trends are often masked by stochastic local fluctuations. Existing methods struggle to reconcile these conflicting resolutions, leading to sub-optimal forecasting. To address this, we propose the Multi-Scale Spatial-Temporal Diffusion Transformer (MS-STDT). Deviating from previous diffusion approaches that treat generation as a monolithic task, we reframe the forward diffusion process as an intrinsic temporal coarse-graining operation. By leveraging the data's multi-scale hierarchy as a structural anchor, we introduce a coarse-to-fine latent guidance strategy that enables the model to reconstruct stable global trends before refining fine-grained details. This ensures physical consistency and generative stability without requiring external labels. Extensive experiments across six real-world datasets confirm that MS-STDT performs the best, demonstrating significant improvements in predictive accuracy and zero-shot robustness against sensor failures. We provide code and data at https://github.com/ZetaoLiPhD/MS-STDT.

Graph pre-training and prompt tuning provide an effective route to label-efficient node classification by learning transferable backbones and adapting them with lightweight prompts. However, existing pre-train-and-prompt pipelines often generalize poorly across graphs with diverse homophily due to two fundamental limitations: (i) spectral bias, where learned representations overemphasize a single frequency band, and (ii) prompt misalignment, where spatial-domain prompts cannot explicitly modulate critical spectral components and may even disrupt frequency-aware backbones. In this paper, we propose SCA-GPPT, a spectrum-aware framework that unifies Spectrum-based Graph Pre-training and Cluster-Augmented Prompt Tuning. First, we present a systematic spectral analysis of graph prompting, revealing the inherent limitations of spatial-domain prompts in capturing attenuated high-frequency signals. Second, we explicitly learn complementary low- and high-frequency spectral filters via parameterized Chebyshev polynomials and employ band-aware contrastive learning to model diverse spectral patterns during pre-training. For downstream adaptation, we freeze the pre-trained backbone and introduce cluster-augmented prompts that directly adapt Chebyshev coefficients while enforcing global structural consistency, enabling stable few-shot transfer across varying homophily regimes. Extensive experiments on real-world benchmarks demonstrate that SCA-GPPT consistently outperforms strong baselines under both transductive and inductive settings. Our code is available at https://anonymous.4open.science/r/SCA-GPPT-17B2.

Heterogeneous Graph Prompt Learning (HGPL) has emerged as a promising paradigm for bridging the gap between the objectives of pre-training foundation models and their downstream applications in heterogeneous graph settings. However, existing HGPL methods are primarily designed for in-domain scenarios, whereas real-world deployments often span multiple domains, and the data used for pre-training and downstream tasks may originate from different distributions. Consequently, the applicability of current HGPL approaches is limited in in-domain settings, and their performance typically degrades when application domains shift. To address this serious limitation, we develop CHoE, a cross-domain HGPL method built upon an expert network. During pre-training, we introduce and train structure-conditioned experts, and during prompt tuning, we propose a structure-aware expert routing and load balancing mechanism to select structurally compatible experts for each meta-path view. In addition, we design a prompt-based semantic fusion module to integrate representations across views for downstream prediction. Extensive experiments show that CHoE consistently improves performance in few-shot cross-domain applications, outperforming all baseline approaches.

Accurate long-term forecasting in complex systems is frequently compromised by dataset-level distribution shifts, where diverse underlying behavioral modes and evolving system states drive the dynamic multivariate time-series. While existing methods predominantly focus on local temporal shifts, they fail to explicitly model the global structural challenge where datasets are composites of distinct operational regimes. In this paper, we propose NEST, a specialized framework designed to model and recompose these evolving structures through a two-phase dense MoE architecture. NEST first facilitates structural specialization by partitioning the dataset into distinct operational regimes through unsupervised clustering in a principled moment-entropy space. We introduce a regime-oriented router mechanism that generates initial expert weights based on temporal content, subsequently refined through geometric modulation to regime centroids. Crucially, rather than acting as monolithic predictors, individual experts function as specialized kernels that capture regime-specific dynamics by evolving unique variate-attention patterns. Extensive evaluations on diverse benchmarks, including heterogeneous network traffic and physical phenomena, demonstrate that NEST consistently achieves state-of-the-art performance. Our code and datasets are available at \url{https://github.com/Aaralshin/NEST}.

Knowledge Graphs (KGs) are extensively used across different domains and in several applications. Often, these KGs are very large in size. Such KGs become unwieldy for tasks such as question answering and visualization. Summarization of KGs offers a viable alternative in such cases. Furthermore, personalized KG summarization is crucial in the current data-driven world as it captures the specific requirements of users based on their query patterns. Since it only maintains relevant information, the personalized summaries of KG are small, resulting in significantly smaller storage requirements and query runtime. In this work, we adapt the coreset theory to create personalized KG summaries. For a given dataset and a user-specific query workload, we present an approach that samples a relevant subset of triples using sensitivity-based importance sampling. We ensure that the subset approximates the characteristics of the full dataset with bounded approximation error. We define sensitivity scores that measure the importance of a triple with respect to a user’s query workload, which are then used by our coreset construction algorithm. We explicitly focus on personalized knowledge graph summarization by constructing summaries independently for each user based on their query behaviour. Our evaluation on Freebase, WikiData, and DBpedia shows that COREKG delivers higher query-answering accuracy and structural coverage than the state-of-the-art methods, such as GLIMPSE, PPR, PEGASUS and APEX² while requiring only a tiny fraction of the original graph.

Flow Matching (FM), as a highly promising generative paradigm, has recently been introduced into sequential recommendation. However, the lack of explicit inter-user supervision in existing FM-based method may lead to an averaged flow phenomenon, where the model tends to produce similar velocity directions for different users during item generation. This greatly undermines the model’s ability to generate personalized item. To address this issue, we propose a Contrastive Flow Matching (ConFM) for sequential reconmendation, aiming to inject inter-user separation signals so as to preserve the discriminability of users’ velocity directions. Specifically, considering the common design where velocities are derived from predicted item representations, we introduce a Representation Contrastive Regularizer in the representation space, which forces the predicted item embeddings of different users to be separated from each other. In addition, we introduce a Velocity Contrastive Regularizer in the induced velocity space, which directly encourages each user’s induced velocity to stay far from other users’ velocity targets, thereby better aligning the generation process with the user’s own interests. Extensive experiments on four datasets demonstrate that ConFM consistently outperforms strong baselines, and it also achieves notable improvements on long-tail items.

Graph Neural Networks (GNNs) are vulnerable to backdoor attacks, where models behave normally on clean data but exhibit targeted misclassifications once specific triggers are activated. Existing backdoor attacks on GNNs mainly focus on enhancing trigger stealthiness or diversifying attack paradigms. However, these methods overlook a fundamental property of GNNs: trigger-induced malicious signals inevitably propagate through graph neighborhoods, causing unintended mispredictions on clean nodes, i.e., Collateral Damage. To address this issue, we propose the Collateral Damage Constrained Graph Backdoor Attack (CDCA), a novel framework that explicitly controls malicious diffusion. Specifically, the proposed method combines neighborhood-aware target node selection with a self-constrained trigger generation strategy to suppress trigger-induced propagation by enforcing prediction consistency on clean K-hop neighboring nodes. Extensive experiments on real-world datasets demonstrate that the proposed method remains effective while significantly reducing collateral damage.

Link prediction is a foundational task in temporal graphs. While temporal graph neural networks exhibit commendable performance, they are often criticized for providing inadequate representations, especially under limited data. Contrastive learning has been introduced as a solution for graph pre-training to mitigate data scarcity. However, the data augmentation techniques on which they depend frequently lead to suboptimal augmentations, manifesting either as over-augmentation or under-augmentation. In light of these challenges, we explore the under-explored domain of contrastive learning of temporal graph transformers and propose a novel model, ContraTGT, which employs a dual-view graph transformer. This transformer is fine-tuned to extract sequences tailored for specific target nodes, encapsulating both spatial and temporal perspectives. To optimize the contrastive learning of this dual-view transformer, we put forth an innovative, learnable data augmentation method. This technique, which involves selective masking of elements within dual-view sequences, generates superior augmentations, thereby amplifying the potency of the contrastive learning approach. Extensive experiments on five public temporal network datasets demonstrate that our model can consistently outperform all baselines, especially in small training set conditions.

Temporal link prediction with temporal graph neural networks (TGNNs) is increasingly used to model spatio-temporal dependencies in temporal graphs and to forecast future interactions among entities. Existing sampling-based training methods typically rely on random negative sampling and pointwise loss formulations, which often lead to suboptimal convergence and limited generalization due to low-quality negative samples. We propose ATNSF, a temporal graph learning framework with a hybrid negative sampling strategy that uses a portion of historical edges as hard negatives. For efficiency, we design an asynchronous parallel training pipeline for scalable optimization and introduce a pairwise sampled softmax loss that contrasts each positive instance with a batch of negatives to learn more discriminative representations. Finally, we theoretically show that jointly designing the loss function and negative sampling strategy is crucial for improving performance and generalization. Extensive experiments across six temporal graph datasets demonstrate that ATNSF improves the average AP from 0.724 to 0.827 (+0.103). Remarkably, it also accelerates training by 1.37× to 6.85×, achieving a 2.57× geometric mean speedup. The source code of this paper can be found at https://github.com/yongqiu-star/ATNSF.

Emotion and intent joint understanding in multimodal conversations (MC-EIU) aims to infer emotion and intent information by leveraging the semantic dependencies among multimodal data. However, prior works largely ignore redundancy interference and suffer from insufficient interaction and inter-task noise propagation due to their reliance on shallow mechanisms. To overcome these limitations, we propose a novel framework named Disentangled Hierarchical Interaction and Adaptive Adjustment (DELTA) for MC-EIU. We first design a Disentangled Feature Denoising module based on orthogonal decomposition to effectively filter out noise and redundancy from heterogeneous data. Second, we propose a Dual-Level Adaptive Adjustment mechanism to dynamically optimize learning dynamics from both modality and instance perspectives. Furthermore, we introduce a Hierarchical Task-Bottleneck Interaction(HTBI) module, which employs a set of progressively compressed bottleneck tokens as a communication hub. This design can effectively simulating the multi-round iterative interaction between emotion and intent tasks. Experiments on the benchmark MC-EIU bilingual dataset demonstrate that our framework significantly outperforms state-of-the-art baselines in both emotion and intent tasks.

Recommendation system technology faces the fundamental challenge of data sparsity. Although incorporating auxiliary textual data works to enrich interactions, lengthy and unstructured item descriptions often fail to depict user interests, as they primarily describe item attributes. Furthermore, the sparse interactions provide incomplete interest patterns, leading to biased recommendations. To address these issues, this work proposes an LLM-summarized interest distillation (SID) model to enrich interactions by interest summarization and retrieval augmentation. Interest summarization leverages large language model to improve user interest descriptions and filters out interest-irrelevant details, generating compact, user-centric interest texts. Retrieval augmentation utilizes semantic neighbors as multiple teachers to adaptively transfer their multimodal collaborative knowledge to augment behaviorally sparse student users, thereby enriching interest learning for recommendation. It enhances interactions both qualitatively, through improved interest descriptions, and quantitatively, through expanded semantic neighbors. Extensive experiments show the superior performance of SID over the state-of-the-art models, demonstrating its effectiveness of interest summarization and retrieval augmentation to improve recommendations.