Meta-Reinforcement Learning (Meta-RL) aims to enable agents to rapidly adapt to new tasks by leveraging prior experience from related ones. However, existing approaches typically assume consistent state and action spaces across tasks, limiting the ability of Meta-RL methods to generalize to environments with diverse morphologies, dynamics, and reward structures, common in real-world applications. To address this, we propose Mixture of Meta-Policies (MoMP), a modular and scalable Meta-RL framework designed for effective knowledge transfer across structurally heterogeneous environments. MoMP represents policies as sparse combinations of shared submodules, where each submodule is itself an attention-based policy block. During meta-training, MoMP learns to specialize and reuse these attention modules by optimizing their task-conditioned activation across multiple environments. Once trained, the shared module can be plugged into new agents to accelerate learning in novel tasks. Sparse activation enables targeted reuse of prior knowledge while mitigating interference, improving both adaptation speed and long-term retention. Experiments across diverse MuJoCo agents show that MoMP significantly outperforms strong meta-RL baselines, highlighting its effectiveness in cross-environment generalization and efficient meta-policy reuse.

Recent efforts have aimed to improve AI models in legal case matching by integrating legal domain knowledge. However, successful legal case matching requires the tacit knowledge of legal practitioners, which is difficult to verbalize and encode into models. This emphasizes the crucial role of involving legal practitioners in high-stakes legal case matching. To address this, we propose a collaborative matching framework called Co-Matching , which encourages both the model and the legal practitioner to participate in the matching process, integrating tacit knowledge. Unlike existing methods that rely solely on the model, Co-Matching allows both the legal practitioner and the model to determine key sentences and then combine them probabilistically. Co-Matching introduces a method called ProtoEM to estimate human decision uncertainty, facilitating the probabilistic combination. Experimental results demonstrate that Co-Matching consistently outperforms existing legal case matching methods, delivering significant performance improvements over human- and model-based matching in isolation (on average, +5.51% and +8.71%, respectively). Further analysis shows that Co-Matching also ensures better human–model collaboration effectiveness. Our study represents an effort in human–model collaboration for the legal case matching task, marking a milestone for future collaborative matching studies.

Medical report generation which extracts pathological information within medical images and subsequently produces diagnostic text autonomously aims to alleviate the workload of medical experts and offers auxiliary support in diagnoses. Despite some preliminary progress have been made, several limitations still persist, including lack of specificity in extracted visual features, insufficient consideration of cross-modal alignment and extensive preparatory work required for prior knowledge. To address these issues, we, in this article, propose a novel deep label-guided graph convolutional network for medical report generation which utilizes disease label to guide to extract pathological information from medical images. To be specific, we first construct graph convolutional network to guide the model to extract the specific visual features based on disease labels, which allowing us to selectively extract disease specificity information resided in medical images. Then, we develop cross-modal alignment module to guide the alignment across medical image, diagnose report and disease label, which enables more accurate generation with more precise description. Besides, we build pre-constructed relational matrix to guide report generation model to learn the relationship between visual features and disease types with minimal additional workload to further reduce intensive workload. Extensive experiments on three benchmark datasets, i.e., IU X-ray, MIMIC-CXR, and COV-CTR, demonstrate that the proposed method outperforms the recent state-of-the-art medical report generation methods. Ours shows a 9.2% improvement in BLEU-4 score on the IU X-ray dataset, and both BLEU-4 and CIDEr scores improve by 6.31% on the MIMIC-CXR dataset. Additionally, the results show that it can be easily to applied and extended to medical image report generation with different modalities.

Generative recommendation systems have recently seen a surge in interest, largely due to the promising advancements in generative AI. As a competitive solution for multi-behavior sequence recommendations, much of the recent research has concentrated on predicting the next item a user will likely interact with using a generative approach. However, these methods often 1). assign multiple residual quantization layers to obtain item codes, which leads to extra storage costs of more codebooks. And 2). explicitly utilize behavior sequences leading to longer sequences, potentially increasing the training time as well as inference time compared with original sequences. In response to these challenges, we introduce theImplicitMulti-BehaviorGenerative recommendation with a mixture of quantization (IMBGen) approach in this paper. Specifically, we have devised aMixtureofQuantization (MoQ) that combines the merits of both residual and parallel quantization for a more effective tokenization process. Additionally, we propose an Implicit Behavior Modeling (IBM) framework, allowing for more efficient integration of users' behaviors into the interacted items. Finally, we conducted extensive experiments on two widely used benchmark datasets and further confirmed our findings with an online A/B test. The results consistently demonstrate the advantages of our approach over other baseline methods.

The vanilla Graph Convolutional Network (GCN) uses a low-pass filter to extract low-frequency signals from graph topology, which may lead to the over-smoothing problem when GCN goes deep. To this end, various methods have been proposed to create an adaptive filter by incorporating an extra filter (e.g., a high-pass filter) extracted from the graph topology. However, these methods heavily rely on topological information and ignore the node attribute space, which severely sacrifices the expressive power of the deep GCNs, especially when dealing with disassortative graphs. In this paper, we propose a cross-space adaptive filter, called CSF, to produce the adaptive-frequency information extracted from both the topology and attribute spaces. Specifically, we first derive a tailored attribute-based high-pass filter that can be interpreted theoretically as a minimizer for semi-supervised kernel ridge regression. Then, we cast the topology-based low-pass filter as a Mercer's kernel within the context of GCNs. This serves as a foundation for combining it with the attribute-based filter to capture the adaptive-frequency information. Finally, we derive the cross-space filter via an effective multiple-kernel learning strategy, which unifies the attribute-based high-pass filter and the topology-based low-pass filter. This helps to address the over-smoothing problem while maintaining effectiveness. Extensive experiments demonstrate that CSF not only successfully alleviates the over-smoothing problem but also promotes the effectiveness of the node classification task. Our code is available at https://github.com/huangzichun/Cross-Space-Adaptive-Filter.

Imbalanced data problem is a classic topic in artificial intelligence. Neural network approaches to solve this problem mostly rely on resampling or reweighting strategies. However, these methods severely suffer from the learning bias in most cases when the empirical representation of known samples is insufficient. One-class learning can provide an ideal classification property to alleviate this critical issue. However, extending one-class learning to imbalanced data presents problems of hypersphere collapse, ambiguous interclass relations, and compact representations. In this paper, a new one-class learning paradigm is proposed for binary imbalanced data classification. Specifically, a neural network is employed to map known samples to a specified attribute space to solve the problems of hypersphere collapse and ambiguous interclass relations. Then, to alleviate the compact representation problem, a dynamic information potential energy is developed to disperse the mapped majority samples to fill the specified region as much as possible. The proposed method is validated on 34 imbalanced datasets with imbalanced ratios ranging from 16.90 to 100.14. The test results show that the proposed method achieves the best performance on more than half of the test datasets.

Graph-based multi-view learning, which has hitherto been used to discover the intrinsic patterns of graph data giving the credit to its convenience of implementation and effectiveness. Note that even though these approaches have been increasingly adopted in multi-view clustering and have generated promising outcomes, they are still faced with the sub-optimal solution. For one thing, multi-view data can be corrupted in the raw feature space. For the other, most existing approaches normally utilize euclidean distance to obtain the similarity between two samples, which can not be the best option for all types of real-world data and leads to inferior results. Therefore, to overcome the aforementioned issues, we integrate multi-metric learning, graph filtering, and subspace learning into a collaborative learning framework for multi-view clustering. Particularly, we prefer to recover a smooth representation of data by graph filtering, which can reserve the geometric structure of the original multi-view data and discard the corruptions simultaneously. Furthermore, instead of using euclidean distance as a Swiss army knife, multiple metrics are utilized to fully exploit the correlation of data based on the smooth representation, hence finally facilitating the downstream clustering task. Extensive experiments on multi-view clustering tasks validate our theoretical findings of ours and prove the improvement of our method over the SOTA approaches.

In multi-view subspace clustering, it is significant to find a common latent space in which the multi-view datasets are located. A number of multi-view subspace clustering methods have been proposed to explore the common latent subspace and achieved promising performance. However, previous multi-view subspace clustering algorithms seldom consider the multi-view consistency and multi-view diversity, let alone take them into consideration simultaneously. In this paper, we propose a novel multi-view subspace clustering by joint measuring the consistency and diversity, which is able to exploit these two complementary criteria seamlessly into a holistic design of clustering algorithms. The proposed model first searches a pure graph for each view by detecting the intrinsic consistent and diverse parts. A consensus graph is then obtained by fusing the multiple pure graphs. Moreover, the consensus graph is structurized to contain exactly$c$connected components where$c$is the number of clusters. In this way, the final clustering result can be obtained directly since each connected component precisely corresponds to an individual cluster. Extensive experimental studies on various datasets manifest that our model achieves comparable performance than the other state-of-the-art methods.

Multi-view clustering aims to reveal the correlation between different input modalities in an unsupervised way. Similarity between data samples can be described by a similarity graph, which governs the quality of multi-view clustering. However, existing multi-view graph learning methods mainly construct similarity graph based on raw features, which are unreliable as real-world datasets usually contain noises, outliers, or even redundant information. In this paper, we formulate a novel model to simultaneously learn a robust structured similarity graph and perform multi-view clustering. The similarity graph is adaptively learned based on a latent representation that is invulnerable to noises and outliers. Furthermore, the similarity graph is enforced to contain a clear structure, i.e., the number of connected components of the target graph is exactly equal to the ground-truth class number. Consequently, the label to each data sample can be directly assigned without any postprocessing. As a result, our model aims at accomplishing three subtasks: latent representation extraction, similarity graph learning, and cluster label allocation, in a unified framework. These three subtasks are seamlessly integrated and can be mutually boosted by each other towards the overall optimal solution. An efficient alternation algorithm is proposed to solve the optimization problem. Experimental results on several benchmark datasets illustrate the effectiveness of the proposed model.

Feature selection refers to choose an optimal non-redundant feature subset with minimal degradation of learning performance and maximal avoidance of data overfitting. The appearance of large data explosion leads to the sequential execution of algorithms are extremely time-consuming, which necessitates the scalable parallelization of algorithms by efficiently exploiting the distributed computational capabilities. In this paper, we present parallel feature selection algorithms underpinned by a rough hypercuboid approach in order to scale for the growing data volumes. Metrics in terms of rough hypercuboid are highly suitable to parallel distributed processing, and fits well with the Apache Spark cluster computing paradigm. Two data parallelism strategies, namely, vertical partitioning and horizontal partitioning, are implemented respectively to decompose the data into concurrent iterative computing streams. Experimental results on representative datasets show that our algorithms significantly faster than its original sequential counterpart while guaranteeing the quality of the results. Furthermore, the proposed algorithms are perfectly capable of exploiting the distributed-memory clusters to accomplish the computation task that fails on a single node due to the memory constraints. Parallel scalability and extensibility analysis have confirmed that our parallelization extends well to process massive amount of data and can scales well with the increase of computational nodes.

Proactive dialogue system is able to lead the conversation to a goal topic and has advantaged potential in bargain, persuasion, and negotiation. Current corpus-based learning manner limits its practical application in real-world scenarios. To this end, we contribute to advancing the study of the proactive dialogue policy to a more natural and challenging setting, i.e., interacting dynamically with users. Further, we call attention to the non-cooperative user behavior - the user talks about off-path topics when he/she is not satisfied with the previous topics introduced by the agent. We argue that the targets of reaching the goal topic quickly and maintaining a high user satisfaction are not always converged, because the topics close to the goal and the topics user preferred may not be the same. Towards this issue, we propose a new solution named I-Pro that can learn Proactive policy in the Interactive setting. Specifically, we learn the trade-off via a learned goal weight, which consists of four factors (dialogue turn, goal completion difficulty, user satisfaction estimation, and cooperative degree). The experimental results demonstrate I-Pro significantly outperforms baselines in terms of effectiveness and interpretability.

Deep learning has been widely applied into image inpainting. However, traditional image processing methods (i.e., patch-based and diffusion-based methods) generally fail to produce visually natural contents and semantically reasonable structures due to ineffectively processing the high-level semantic information of images. To solve the problem, we propose a stacked generator networks assisted by patch discriminator for image inpainting by multistage. In the proposed method, our generator network mainly consists of three-layer stacked encoder-decoder architecture, which could fuse different level feature information and achieve image inpainting via a coarse-to-fine hierarchical representation. Meanwhile, we split the masked image into different patches in each layer, which could effectively enlarge the receptive field and extract more useful features of images. Moreover, the patch discriminator is introduced to judge the patches of inpainting image are real or fake. In this way, our network can effectively utilize the semantic information to complete a fine result. Furthermore, both perceptual loss and style loss are used to improve the inpainting results in verse. Experimental results on Places2 and Paris StreetView illustrate that our approach could generate high-quality inpainting results, and our method is more effective than the existing image inpainting methods.

Graph learning has emerged as a promising technique for multi-view clustering due to its efficiency of learning a unified graph from multiple views. Previous multi-view graph learning methods mainly try to exploit the multi-view consistency to boost learning performance. However, these methods ignore the prevalent multi-view diversity which may be induced by noise, corruptions, or even view-specific attributes. In this paper, we propose to simultaneously and explicitly leverage the multi-view consistency and the multi-view diversity in a unified framework. The consistent parts are further fused to our target graph with a clear clustering structure, on which the cluster label to each instance can be directly allocated without any postprocessing such as$k$-means in classical spectral clustering. In addition, our model can automatically assign suitable weight for each view based on its clustering capacity. By leveraging the subtasks of measuring the diversity of graphs, integrating the consistent parts with automatically learned weights, and allocating cluster label to each instance in a joint framework, each subtask can be alternately boosted by utilizing the results of the others towards an overall optimal solution. Extensive experimental results on several benchmark multi-view datasets demonstrate the effectiveness of our model in comparison to several state-of-the-art algorithms.