In this paper, we develop a novel local graph pooling method, namely the Separated Subgraph-based Hierarchical Pooling (SSHPool), for graph classification. We commence by assigning the nodes of a sample graph into different clusters, resulting in a family of separated subgraphs. We individually employ the local graph convolution units as the local structure to further compress each subgraph into a coarsened node, transforming the original graph into a coarsened graph. Since these subgraphs are separated by different clusters and the structural information cannot be propagated between them, the local convolution operation can significantly avoid the over-smoothing problem caused by message passing through edges in most existing Graph Neural Networks (GNNs). By hierarchically performing the proposed procedures on the resulting coarsened graph, the proposed SSHPool can effectively extract the hierarchical global features of the original graph structure, encapsulating rich intrinsic structural characteristics. Furthermore, we develop an end-to-end GNN framework associated with the SSHPool module for graph classification. Experimental results demonstrate the superior performance of the proposed model on real-world datasets.

Safety-aligned large language models (LLMs) often generate refusal responses to harmless queries due to the over-refusal problem.However, existing methods for mitigating overrefusal cannot maintain a low refusal ratio for harmless queries while keeping a high refusal ratio for malicious ones.In this paper, we analyze how system prompts with varying safety levels affect LLM refusal behaviors when facing over-refusal queries.A key observation is that, when LLMs suffer from the over-refusal issue, non-refusal tokens remain present in the next-token candidate list, but the model systematically fails to select them, despite the generation of refusal tokens.Based on this observation, we propose a trainingfree and model-agnostic approach, Adaptive Contrastive Decoding (AdaCD), to mitigate over-refusal while maintaining LLM safety.First, AdaCD compares the output distributions of the LLM with or without an extreme safety system prompt to refine the refusal token distribution.Second, we introduce an adaptive contrastive decoding strategy that dynamically incorporates or removes the refusal token distribution, adaptively boosting the probability of selecting refusal or non-refusal tokens.Experimental results on five benchmark datasets show that, on average, AdaCD reduces the refusal ratio for over-refusal queries by 10.35%, yet still increases the refusal ratio for malicious queries by 0.13%.

Large language models (LLMs) are increasingly adopted as the backbone of recommender systems. However, user–item interactions in real-world scenarios are non-stationary, making preference drift over time inevitable. Existing model update strategies mainly rely on global fine-tuning or pointwise editing, but they face two fundamental challenges: (i) imbalanced update granularity, where global updates perturb behaviors unrelated to the target while pointwise edits fail to capture broader preference shifts; (ii) unstable incremental updates, where repeated edits interfere with prior adaptations, leading to catastrophic forgetting and inconsistent recommendations. To address these issues, we propose Region-Aware Incremental Editing (RAIE), a plug-in framework that freezes the backbone model and performs region-level updates. RAIE first constructs semantically coherent preference regions via spherical k-means in the representation space. It then assigns incoming sequences to regions via confidence-aware gating and performs three localized edit operations-Update, Expand, and Add-to dynamically revise the affected region. Each region is equipped with a dedicated Low-Rank Adaptation (LoRA) module, which is trained only on the region's updated data. During inference, RAIE routes each user sequence to its corresponding region and activates the region-specific adapter for prediction. Experiments on two benchmark datasets under a time-sliced protocol that segments data into Set-up (S), Finetune (F), and Test (T) show that RAIE significantly outperforms state-of-the-art baselines while effectively mitigating forgetting. These results demonstrate that region-aware editing offers an accurate and scalable mechanism for continual adaptation in dynamic recommendation scenarios.

Recommendation algorithms have been extensively applied in multiple areas. However, user-level uncertainty in implicit feedback introduce false-positive signals, misaligning interactions with true preferences and introducing noise. This makes it challenging for traditional recommendation methods to achieve both robust and accurate performance. In this manuscript, we propose a semi-supervised co-training algorithm for denoising learning in the recommender system, which incorporates both supervised learning and semi-supervised learning in a cooperative way. We first adopt a Gaussian Mixture Model as a confidence estimation module to partition the implicit feedback into two disjoint datasets: a reliable dataset and an unreliable dataset, based on the intrinsic features of the feedback. To achieve doubly robust learning, we design an iterative cross co-training module that consists of two key components: a two-stage reliable learning process and a cross-sample transmission mechanism. The two-stage reliable learning process enables semi-supervised training on both the reliable and unreliable datasets. Meanwhile, the cross-sample transmission mechanism iteratively transfers hard yet clean samples between dual networks, enhancing robustness through mutual supervision during joint learning. Extensive experiments are conducted using clean test sets extracted from four real-world explicit feedback datasets to validate our denoising method, which demonstrates superior effectiveness across all datasets.

Graph-based representations are powerful tools for analyzing structured data. In this paper, we propose a novel model to learn Deep Hierarchical Attention-based Kernelized Representations (DHAKR) for graph classification. To this end, we commence by learning an assignment matrix to hierarchically map the substructure invariants into a set of composite invariants, resulting in hierarchical kernelized representations for graphs. Moreover, we introduce the feature-channel attention mechanism to capture the interdependencies between different substructure invariants that will be converged into the composite invariants, addressing the shortcoming of discarding the importance of different substructures arising in most existing R-convolution graph kernels. We show that the proposed DHAKR model can adaptively compute the kernel-based similarity between graphs, identifying the common structural patterns over all graphs. Experiments demonstrate the effectiveness of the proposed DHAKR model.

Visually-aware recommender system (VARS) has become increasingly prevalent in various online services by integrating visual features of items to enhance recommendation quality. However, VARS introduces new security vulnerabilities and malicious attackers can perform visual shilling attacks to manipulate recommendation lists via uploading generated images with visually imperceptible perturbations. While prior research has explored such threats to help service providers enhance their systems, existing visual shilling attack methods still suffer from uncontrolled pixel-space perturbation, energy dispersion dilemma and semantic misalignment in reference selection. In this work, we present Semantic-Constrained Diffusion Adversarial Generation (SC-DAG) for visual shilling attacks. SC-DAG overcomes key limitations of previous methods by focusing perturbations on semantically meaningful image regions through contour-aware segmentation, guiding adversarial generation in latent space using a conditional diffusion process, and performing a hybrid reference image selection strategy that balances popularity and semantic similarity. Extensive experiments on performing visual shilling attacks against multiple VARS models show that SC-DAG achieves state-of-the-art attack performance in elevating target items' ranking, while maintaining strong perceptual indistinguishability and minimal impact on overall recommendation performance of the system. Our work offers insights into leveraging structured semantic priors for more sophisticated adversarial manipulations against VARS and also highlights the necessity for developing more robust VARS models resilient to visual shilling attacks. We provide our implementation at https://github.com/KDEGroup/SC-DAG.

Graph Neural Networks (GNNs) have emerged as powerful tools for graph learning, and one key challenge arising in GNNs is the development of effective pooling operations for learning meaningful graph representations. In this paper, we propose a novel Edge-Node Attention-based Hierarchical Pooling (ENAHPool) operation for GNNs. Unlike existing cluster-based pooling methods that suffer from ambiguous node assignments and uniform edge-node information aggregation, ENAHPool assigns each node exclusively to a cluster and employs attention mechanisms to perform weighted aggregation of both node features within clusters and edge connectivity strengths between clusters, resulting in more informative hierarchical representations. To further enhance the model performance, we introduce a Multi-Distance Message Passing Neural Network (MD-MPNN) that utilizes edge connectivity strength information to enable direct and selective message propagation across multiple distances, effectively mitigating the over-squashing problem in classical MPNNs. Experimental results demonstrate the effectiveness of the proposed method.

In this paper, we propose a family of novel Deep Hierarchical Transitive-Aligned Graph Kernels (DHTAGK) for graph classification. To this end, we commence by developing a new Hierarchical Aligned Graph Auto-Encoder (HA-GAE) to construct transitive-aligned embedding graphs that encapsulate the structural correspondence information between graphs. The DHTAGK kernels then measure either the Jensen-Shannon Divergence between the adjacency matrices or the Gaussian kernel between the node feature matrices of the embedding graphs. Unlike the classical R-convolution kernels and node-based alignment kernels, the DHTAGK kernels can capture the transitive structural correspondence information and thus ensure the positive definiteness. Furthermore, the HA-GAE enables the DHTAGK kernels to simultaneously reflect both local and global graph structures and identify common structural patterns. Experimental results show that the DHTAGK kernels outperform state-of-the-art graph kernels and deep learning methods on benchmark datasets.

In the rapidly evolving field of Artificial Intelligence Generated Content (AIGC), a central challenge is distinguishing AI-synthesized images from natural images. Despite the impressive capabilities of advanced AI generative models in producing visually compelling content, significant discrepancies remain when compared to natural images. To systematically investigate and quantify these differences, we construct a large-scale multimodal dataset named DANI, comprising 5,000 natural images and over 440,000 AI-generated image (AIGI) samples produced by nine representative models using both unimodal and multimodal prompts, including Text-to-Image (T2I), Text-and-Image-to-Image (I2I), and Text and Image-to-Image (TI2I). We then introduce D-Judge, a benchmark designed to answer the critical question: how far are AI-generated images from truly realistic images? Our fine-grained evaluation framework assesses DANI across five key dimensions: naive visual quality, semantic alignment, aesthetic appeal, downstream task applicability, and coordinated human validation. Extensive experiments reveal substantial discrepancies across these dimensions, highlighting the importance of aligning quantitative metrics with human judgment to achieve a comprehensive understanding of AI-generated image quality. The code and dataset are publicly available at: https://github.com/ryliu68/DJudge, and https://huggingface.co/datasets/Renyang/DANI.

Large Language Models (LLMs) have revolutionized recommender systems by offering highly personalized and context-aware suggestions. However, their inherent biases pose significant challenges in sensitive scenarios like job recommendation, potentially compromising fairness and resulting in harmful effects on both users and platforms. While previous studies have explored fairness issues in LLM-based job recommendations, they often focus on limited dimensions. We introduce FairWork, a comprehensive fairness evaluation framework to examine LLM-based recommender system from both the user's and recruiter's perspectives, employing fairness metrics to assess how sensitive user attributes influence job recommendations. The system allows stakeholders such as recruitment platforms and job seekers to upload personalized profiles and job descriptions for fairness analysis. By integrating specific job requirements and user-driven data inputs, FairWork captures the relationship between candidate qualifications and job demands. This framework provides a robust foundation for evaluating fairness in LLM-based job recommender systems and supports future research on bias mitigation strategies. The demo is available at https://github.com/chenzhouli/FairWork.

Knowledge Distillation (KD) transfers knowledge from large models to small models and has recently achieved remarkable success. However, the reliability of existing KD methods in real-world applications, especially under distribution shift, remains underexplored. Distribution shift refers to the data distribution drifts between the training and testing phases, and this can adversely affect the efficacy of KD. In this paper, we propose a unified and systematic framework ShiftKD to benchmark KD against two general distributional shifts: diversity and correlation shift. The evaluation benchmark covers more than 30 methods from algorithmic, data-driven, and optimization perspectives for five benchmark datasets. Our development of ShiftKD conducts extensive experiments and reveals strengths and limitations of current SOTA KD methods. More importantly, we thoroughly analyze key factors in student model training process, including data augmentation, pruning methods, optimizers, and evaluation metrics. We believe ShiftKD could serve as an effective benchmark for assessing KD in real-world scenarios, thus driving the development of more robust KD methods in response to evolving demands. The code will be made available upon publication.

Heterogeneous Information Network based Recommender Systems (HIN-based RS) can model the complex interactions between different objects in RS. However, existing models assume HIN is invariable and merely use HIN as a data source for assisting recommendation. In this paper, we summarize our multi-task learning framework MTRec for recommendation over HIN. MTRec relies on the self-attention mechanism to learn the semantics of meta-paths in HIN and jointly optimizes the tasks of both recommendation and link prediction. Using a Bayesian task weight learner, MTRec is able to achieve the balance of two tasks during optimization automatically. Moreover, MTRec provides good interpretability of recommendation through a “translation” mechanism which is used to model the three-way interactions among users, items and the meta-paths connecting them. Experimental results demonstrate the effectiveness and the robustness of MTRec over state-of-the-art models.

Code search plays a crucial role in software development, enabling developers to retrieve and reuse code using natural language queries. While the performance of code search models improves with an increase in high-quality data, obtaining such data can be challenging and expensive. Recently, large language models (LLMs) such as ChatGPT have made remarkable progress in both natural and programming language understanding and generation, offering user-friendly interaction via simple prompts. Inspired by these advancements, we propose a novel approach ChatDANCE, which utilizes high-quality and diverse augmented data generated by a large language model and leverages a filtering mechanism to eliminate low-quality augmentations. Specifically, we first propose a set of ChatGPT prompting rules that are specifically designed for source code and queries. Then, we leverage ChatGPT to rewrite code and queries based on the according prompts and then propose a filtering mechanism which trains a cross-encoder from the backbone model UniXcoder to filter out code and query pairs with low matching scores. Finally, we re-train the backbone model using the obtained high-quality augmented data. Experimental results show that ChatDANCE achieves state-of-the-art performance, improving the best baseline by 13.2% (R@1) and 7% (MRR). Surprisingly, we find that this augment-filter-retrain strategy enables the backbone model (UniXcoder) to self-grow. Moreover, extensive experiments show the effectiveness of each component and ChatDANCE has stable performance under different hyperparameter settings. In addition, we conduct qualitative and quantitative analyses to investigate why ChatDANCE works well and find that it learns a more uniform distribution of representations and effectively aligns the code and query spaces. We have made the code and data anonymously available at https://anonymous.4open.science/r/ChatDANCE.

As inclusions are inevitable from the material-producing processes, an engineering concept regarding multiple features of them is needed for material design. In this study, a unique approach integrating physical-meaningful microstructure-sensitive models with the machine-learning-based data-driven model is proposed to reveal the complex relationship between the fatigue life of materials with intrinsic features of inclusions including size, stiffness, thermal properties, and extrinsic stress amplitudes. This high-fidelity presentation of the relation of these variables enables a detailed and systematic analysis of the effects of inclusions on fatigue life. The data-based phase map provides a designing envelope of inclusion features for fatigue-resistant steels.

Recently, explainable recommendation has attracted increasing attentions, which can make the recommender system more transparent and improve user satisfactions by recommending products with useful explanations. However, existing methods trend to trade-off between the recommendation accuracy and the interpretability of recommendation results. In this manuscript, we propose Knowledge Enhanced Graph Neural Networks (KEGNN) for explainable recommendation. Semantic knowledge from the external knowledge base is leveraged into representation learning of three sides, respectively user, items and user-item interactions, and the knowledge enhanced semantic embedding are exploited to initialize the user/item entities and user-item relations of one constructed user behavior graph. We design a graph neural networks based user behavior learning and reasoning model to perform both semantic and relational knowledge propagation and reasoning over the user behavior graph for comprehensive understanding of user behaviors. On the top of comprehensive representations of users/items and user-item interactions, hierarchical neural collaborative filtering layers are developed for precise rating prediction, and one generation-mode and copy-mode combined generator is devised for human-like semantic explanation generation by integrating the copy mechanism into gated recurrent neural networks. Quantitative and qualitative results demonstrate the superiority of KEGNN over the state-of-art methods, and the explainability and interpretability of our method.

Action recognition has been traditionally treated as a high-level video classification problem. However, such a manner lacks the detailed and semantic understanding of body movement, which is the critical knowledge to explain and infer complex human actions. To fill this gap, we propose to summarize a novel visual knowledge graph from over 15M detailed human annotations, for describing action as the distinct composition of body parts, part movements and interactive objects in videos. Based on it, we design a generic multi-modal Action Knowledge Understanding (AKU) framework, which can progressively infer human actions from body part movements in the videos, with assistance of visual-driven semantic knowledge mining. Finally, we validate AKU on the recent Kinetics-TPS benchmark, which contains body part parsing annotations for detailed understanding of human action in videos. The results show that, our AKU significantly boosts various video backbones with explainable action knowledge in both supervised and few shot settings, and outperforms the recent knowledge-based action recognition framework, e.g., our AKU achieves 83.9% accuracy on Kinetics-TPS while PaStaNet achieves 63.8% accuracy under the same backbone. The codes and models will be released at https://github.com/mayuelala/AKU.

Traditional recommender systems (RS) only consider homogeneous data and cannot fully model heterogeneous information of complex objects and relations. Recent advances in the study of Heterogeneous Information Network (HIN) have shed some light on how to leverage heterogeneous information in RS. However, existing HIN-based recommendation models assume HIN is invariable and merely use HIN as a data source for assisting recommendation, which limits their performance. In this paper, we propose a multi-task learning framework, called MTRec, for recommendation over HIN. MTRec relies on self-attention mechanism to learn the semantics of meta-paths in HIN and jointly optimizes the tasks of both recommendation and link prediction. Using a Bayesian task weight learner, MTRec is able to achieve the balance of two tasks during optimization automatically. Moreover, MTRec provides good interpretabilities of recommendation through a “translation” mechanism which is used to model the three-way interactions among users, items and the meta-paths connecting them. Experimental results demonstrate the superiority of MTRec over state-of-the-art HIN-based recommendation models, and the case studies we provide illustrate that MTRec enhances the explainability of RS.