Hui Wang

Mingyang Hu, Fajie Yuan, Kevin K. Yang et al. · microsoft-research

Large-scale Protein Language Models (PLMs) have improved performance in protein prediction tasks, ranging from 3D structure prediction to various function predictions. In particular, AlphaFold, a ground-breaking AI system, could potentially reshape structural biology. However, the utility of the PLM module in AlphaFold, Evoformer, has not been explored beyond structure prediction. In this paper, we investigate the representation ability of three popular PLMs: ESM-1b (single sequence), MSA-Transformer (multiple sequence alignment) and Evoformer (structural), with a special focus on Evoformer. Specifically, we aim to answer the following key questions: (i) Does the Evoformer trained as part of AlphaFold produce representations amenable to predicting protein function? (ii) If yes, can Evoformer replace ESM-1b and MSA-Transformer? (ii) How much do these PLMs rely on evolution-related protein data? In this regard, are they complementary to each other? We compare these models by empirical study along with new insights and conclusions. All code and datasets for reproducibility are available at https://github.com/elttaes/Revisiting-PLMs.

Shengming Li, Guangcong Zheng, Hui Wang et al.

Denoising Diffusion Probabilistic Model (DDPM) is able to make flexible conditional image generation from prior noise to real data, by introducing an independent noise-aware classifier to provide conditional gradient guidance at each time step of denoising process. However, due to the ability of classifier to easily discriminate an incompletely generated image only with high-level structure, the gradient, which is a kind of class information guidance, tends to vanish early, leading to the collapse from conditional generation process into the unconditional process. To address this problem, we propose two simple but effective approaches from two perspectives. For sampling procedure, we introduce the entropy of predicted distribution as the measure of guidance vanishing level and propose an entropy-aware scaling method to adaptively recover the conditional semantic guidance. For training stage, we propose the entropy-aware optimization objectives to alleviate the overconfident prediction for noisy data.On ImageNet1000 256x256, with our proposed sampling scheme and trained classifier, the pretrained conditional and unconditional DDPM model can achieve 10.89% (4.59 to 4.09) and 43.5% (12 to 6.78) FID improvement respectively. The code is available at https://github.com/ZGCTroy/ED-DPM.

M. L. Menezes, A. Samara, L. Galway et al.

One of the challenges in virtual environments is the difficulty users have in interacting with these increasingly complex systems. Ultimately, endowing machines with the ability to perceive users emotions will enable a more intuitive and reliable interaction. Consequently, using the electroencephalogram as a bio-signal sensor, the affective state of a user can be modelled and subsequently utilised in order to achieve a system that can recognise and react to the user's emotions. This paper investigates features extracted from electroencephalogram signals for the purpose of affective state modelling based on Russell's Circumplex Model. Investigations are presented that aim to provide the foundation for future work in modelling user affect to enhance interaction experience in virtual environments. The DEAP dataset was used within this work, along with a Support Vector Machine and Random Forest, which yielded reasonable classification accuracies for Valence and Arousal using feature vectors based on statistical measurements and band power from the ź, \b{eta}, ź, and źź waves and High Order Crossing of the EEG signal.

Sicen Liu, Xiaolong Wang, JIngcheng Du et al.

Effectively medication recommendation with complex multimorbidity conditions is a critical task in healthcare. Most existing works predicted medications based on longitudinal records, which assumed the information transmitted patterns of learning longitudinal sequence data are stable and intra-visit medical events are serialized. However, the following conditions may have been ignored: 1) A more compact encoder for intra-relationship in the intra-visit medical event is urgent; 2) Strategies for learning accurate representations of the variable longitudinal sequences of patients are different. In this paper, we proposed a novel Sample-adaptive Hierarchical medicAtion Prediction nEtwork, termed SHAPE, to tackle the above challenges in the medication recommendation task. Specifically, we design a compact intra-visit set encoder to encode the relationship in the medical event for obtaining visit-level representation and then develop an inter-visit longitudinal encoder to learn the patient-level longitudinal representation efficiently. To endow the model with the capability of modeling the variable visit length, we introduce a soft curriculum learning method to assign the difficulty of each sample automatically by the visit length. Extensive experiments on a benchmark dataset verify the superiority of our model compared with several state-of-the-art baselines.

Sicen Liu, Xiaolong Wang, Yang Xiang et al.

Medical event prediction (MEP) is a fundamental task in the medical domain, which needs to predict medical events, including medications, diagnosis codes, laboratory tests, procedures, outcomes, and so on, according to historical medical records. The task is challenging as medical data is a type of complex time series data with heterogeneous and temporal irregular characteristics. Many machine learning methods that consider the two characteristics have been proposed for medical event prediction. However, most of them consider the two characteristics separately and ignore the correlations among different types of medical events, especially relations between historical medical events and target medical events. In this paper, we propose a novel neural network based on attention mechanism, called cross-event attention-based time-aware network (CATNet), for medical event prediction. It is a time-aware, event-aware and task-adaptive method with the following advantages: 1) modeling heterogeneous information and temporal information in a unified way and considering temporal irregular characteristics locally and globally respectively, 2) taking full advantage of correlations among different types of events via cross-event attention. Experiments on two public datasets (MIMIC-III and eICU) show CATNet can be adaptive with different MEP tasks and outperforms other state-of-the-art methods on various MEP tasks. The source code of CATNet will be released after this manuscript is accepted.

Yu Wang, Hui Wang, Jiake Ge et al.

Exact subgraph matching on large-scale graphs remains a challenging problem due to high computational complexity and distributed system constraints. Existing GNN-based path embedding (GNN-PE) frameworks achieve efficient exact matching on single machines but lack scalability and optimization for distributed environments. To address this gap, we propose three core innovations to extend GNN-PE to distributed systems: (1) a lightweight dynamic correlation-aware load balancing and hot migration mechanism that fuses multi-dimensional metrics (CPU, communication, memory) and guarantees index consistency; (2) an online incremental learning-based multi-GPU collaborative dynamic caching strategy with heterogeneous GPU adaptation and graph-structure-aware replacement; (3) a query plan ranking method driven by dominance embedding pruning potential (PE-score) that optimizes execution order. Through METIS partitioning, parallel offline preprocessing, and lightweight metadata management, our approach achieves "minimum edge cut + load balancing + non-interruptible queries" in distributed scenarios (tens of machines), significantly improving the efficiency and stability of distributed subgraph matching.

Hui Wang, Yueyang li, Haichi Luo

Fine-Grained Visual Classification (FGVC) is known as a challenging task due to subtle differences among subordinate categories. Many current FGVC approaches focus on identifying and locating discriminative regions by using the attention mechanism, but neglect the presence of unnecessary features that hinder the understanding of object structure. These unnecessary features, including 1) ambiguous parts resulting from the visual similarity in object appearances and 2) noninformative parts (e.g., background noise), can have a significant adverse impact on classification results. In this paper, we propose the Semantic Feature Integration network (SFI-Net) to address the above difficulties. By eliminating unnecessary features and reconstructing the semantic relations among discriminative features, our SFI-Net has achieved satisfying performance. The network consists of two modules: 1) the multi-level feature filter (MFF) module is proposed to remove unnecessary features with different receptive field, and then concatenate the preserved features on pixel level for subsequent disposal; 2) the semantic information reconstitution (SIR) module is presented to further establish semantic relations among discriminative features obtained from the MFF module. These two modules are carefully designed to be light-weighted and can be trained end-to-end in a weakly-supervised way. Extensive experiments on four challenging fine-grained benchmarks demonstrate that our proposed SFI-Net achieves the state-of-the-arts performance. Especially, the classification accuracy of our model on CUB-200-2011 and Stanford Dogs reaches 92.64% and 93.03%, respectively.

Hui Wang, Abdallah Saffidine, Tristan Cazenave

Recent work proposed the UCTMAXSAT algorithm to address Maximum Satisfiability Problems (MaxSAT) and shown improved performance over pure Stochastic Local Search algorithms (SLS). UCTMAXSAT is based on Monte Carlo Tree Search but it uses SLS instead of purely random playouts. In this work, we introduce two algorithmic variations over UCTMAXSAT. We carry an empirical analysis on MaxSAT benchmarks from recent competitions and establish that both ideas lead to performance improvements. First, a nesting of the tree search inspired by the Nested Monte Carlo Search algorithm is effective on most instance types in the benchmark. Second, we observe that using a static flip limit in SLS, the ideal budget depends heavily on the instance size and we propose to set it dynamically. We show that it is a robust way to achieve comparable performance on a variety of instances without requiring additional tuning.

Jiahui Wang, Zhenyou Wang, Shanna Zhuang et al.

Temporal convolutions have been the paradigm of choice in action segmentation, which enhances long-term receptive fields by increasing convolution layers. However, high layers cause the loss of local information necessary for frame recognition. To solve the above problem, a novel encoder-decoder structure is proposed in this paper, called Cross-Enhancement Transformer. Our approach can be effective learning of temporal structure representation with interactive self-attention mechanism. Concatenated each layer convolutional feature maps in encoder with a set of features in decoder produced via self-attention. Therefore, local and global information are used in a series of frame actions simultaneously. In addition, a new loss function is proposed to enhance the training process that penalizes over-segmentation errors. Experiments show that our framework performs state-of-the-art on three challenging datasets: 50Salads, Georgia Tech Egocentric Activities and the Breakfast dataset.

Yunpeng Zhang, Zhengyou Wang, Shanna Zhuang et al.

Gait recognition, which can realize long-distance and contactless identification, is an important biometric technology. Recent gait recognition methods focus on learning the pattern of human movement or appearance during walking, and construct the corresponding spatio-temporal representations. However, different individuals have their own laws of movement patterns, simple spatial-temporal features are difficult to describe changes in motion of human parts, especially when confounding variables such as clothing and carrying are included, thus distinguishability of features is reduced. In this paper, we propose the Motion Excitation Module (MEM) to guide spatio-temporal features to focus on human parts with large dynamic changes, MEM learns the difference information between frames and intervals, so as to obtain the representation of temporal motion changes, it is worth mentioning that MEM can adapt to frame sequences with uncertain length, and it does not add any additional parameters. Furthermore, we present the Fine Feature Extractor (FFE), which independently learns the spatio-temporal representations of human body according to different horizontal parts of individuals. Benefiting from MEM and FFE, our method innovatively combines motion change information, significantly improving the performance of the model under cross appearance conditions. On the popular dataset CASIA-B, our proposed Motion Gait is better than the existing gait recognition methods.

Zhihao Du, Yuxuan Wang, Qian Chen et al.

In our previous work, we introduced CosyVoice, a multilingual speech synthesis model based on supervised discrete speech tokens. By employing progressive semantic decoding with two popular generative models, language models (LMs) and Flow Matching, CosyVoice demonstrated high prosody naturalness, content consistency, and speaker similarity in speech in-context learning. Recently, significant progress has been made in multi-modal large language models (LLMs), where the response latency and real-time factor of speech synthesis play a crucial role in the interactive experience. Therefore, in this report, we present an improved streaming speech synthesis model, CosyVoice 2, which incorporates comprehensive and systematic optimizations. Specifically, we introduce finite-scalar quantization to improve the codebook utilization of speech tokens. For the text-speech LM, we streamline the model architecture to allow direct use of a pre-trained LLM as the backbone. In addition, we develop a chunk-aware causal flow matching model to support various synthesis scenarios, enabling both streaming and non-streaming synthesis within a single model. By training on a large-scale multilingual dataset, CosyVoice 2 achieves human-parity naturalness, minimal response latency, and virtually lossless synthesis quality in the streaming mode. We invite readers to listen to the demos at https://funaudiollm.github.io/cosyvoice2.

Hui Wang, Jieren Cheng, Yichen Xu et al.

Robotic arms are widely used in automatic industries. However, with wide applications of deep learning in robotic arms, there are new challenges such as the allocation of grasping computing power and the growing demand for security. In this work, we propose a robotic arm grasping approach based on deep learning and edge-cloud collaboration. This approach realizes the arbitrary grasp planning of the robot arm and considers the grasp efficiency and information security. In addition, the encoder and decoder trained by GAN enable the images to be encrypted while compressing, which ensures the security of privacy. The model achieves 92% accuracy on the OCID dataset, the image compression ratio reaches 0.03%, and the structural difference value is higher than 0.91.

Md. Najib Hasan, Imran Ahmad, Sourav Basak Shuvo et al.

Medical image classifiers detect gastrointestinal diseases well, but they do not explain their decisions. Large language models can generate clinical text, yet they struggle with visual reasoning and often produce unstable or incorrect explanations. This leaves a gap between what a model sees and the type of reasoning a clinician expects. We introduce a framework that links image classification with structured clinical reasoning. A new hybrid model, MobileCoAtNet, is designed for endoscopic images and achieves high accuracy across eight stomach-related classes. Its outputs are then used to drive reasoning by several LLMs. To judge this reasoning, we build two expert-verified benchmarks covering causes, symptoms, treatment, lifestyle, and follow-up care. Thirty-two LLMs are evaluated against these gold standards. Strong classification improves the quality of their explanations, but none of the models reach human-level stability. Even the best LLMs change their reasoning when prompts vary. Our study shows that combining DL with LLMs can produce useful clinical narratives, but current LLMs remain unreliable for high-stakes medical decisions. The framework provides a clearer view of their limits and a path for building safer reasoning systems. The complete source code and datasets used in this study are available at https://github.com/souravbasakshuvo/DL3M.

Hui Wang, Michael Emmerich, Mike Preuss et al.

Since AlphaGo and AlphaGo Zero have achieved breakground successes in the game of Go, the programs have been generalized to solve other tasks. Subsequently, AlphaZero was developed to play Go, Chess and Shogi. In the literature, the algorithms are explained well. However, AlphaZero contains many parameters, and for neither AlphaGo, AlphaGo Zero nor AlphaZero, there is sufficient discussion about how to set parameter values in these algorithms. Therefore, in this paper, we choose 12 parameters in AlphaZero and evaluate how these parameters contribute to training. We focus on three objectives~(training loss, time cost and playing strength). For each parameter, we train 3 models using 3 different values~(minimum value, default value, maximum value). We use the game of play 6$\times$6 Othello, on the AlphaZeroGeneral open source re-implementation of AlphaZero. Overall, experimental results show that different values can lead to different training results, proving the importance of such a parameter sweep. We categorize these 12 parameters into time-sensitive parameters and time-friendly parameters. Moreover, through multi-objective analysis, this paper provides an insightful basis for further hyper-parameter optimization.

Hui Wang, Michael Emmerich, Aske Plaat

After the recent groundbreaking results of AlphaGo and AlphaZero, we have seen strong interests in deep reinforcement learning and artificial general intelligence (AGI) in game playing. However, deep learning is resource-intensive and the theory is not yet well developed. For small games, simple classical table-based Q-learning might still be the algorithm of choice. General Game Playing (GGP) provides a good testbed for reinforcement learning to research AGI. Q-learning is one of the canonical reinforcement learning methods, and has been used by (Banerjee $\&$ Stone, IJCAI 2007) in GGP. In this paper we implement Q-learning in GGP for three small-board games (Tic-Tac-Toe, Connect Four, Hex)\footnote{source code: https://github.com/wh1992v/ggp-rl}, to allow comparison to Banerjee et al.. We find that Q-learning converges to a high win rate in GGP. For the $ε$-greedy strategy, we propose a first enhancement, the dynamic $ε$ algorithm. In addition, inspired by (Gelly $\&$ Silver, ICML 2007) we combine online search (Monte Carlo Search) to enhance offline learning, and propose QM-learning for GGP. Both enhancements improve the performance of classical Q-learning. In this work, GGP allows us to show, if augmented by appropriate enhancements, that classical table-based Q-learning can perform well in small games.

Zhiwei Lin, Hui Wang, Cees H. Elzinga

Preference orderings are orderings of a set of items according to the preferences (of judges). Such orderings arise in a variety of domains, including group decision making, consumer marketing, voting and machine learning. Measuring the mutual information and extracting the common patterns in a set of preference orderings are key to these areas. In this paper we deal with the representation of sets of preference orderings, the quantification of the degree to which judges agree on their ordering of the items (i.e. the concordance), and the efficient, meaningful description of such sets. We propose to represent the orderings in a subsequence-based feature space and present a new algorithm to calculate the size of the set of all common subsequences - the basis of a quantification of concordance, not only for pairs of orderings but also for sets of orderings. The new algorithm is fast and storage efficient with a time complexity of only $O(Nn^2)$ for the orderings of $n$ items by $N$ judges and a space complexity of only $O(\min\{Nn,n^2\})$. Also, we propose to represent the set of all $N$ orderings through a smallest set of covering preferences and present an algorithm to construct this smallest covering set. The source code for the algorithms is available at https://github.com/zhiweiuu/secs

Zhihao Du, Changfeng Gao, Yuxuan Wang et al.

In our prior works, we introduced a scalable streaming speech synthesis model, CosyVoice 2, which integrates a large language model (LLM) and a chunk-aware flow matching (FM) model, and achieves low-latency bi-streaming speech synthesis and human-parity quality. Despite these advancements, CosyVoice 2 exhibits limitations in language coverage, domain diversity, data volume, text formats, and post-training techniques. In this paper, we present CosyVoice 3, an improved model designed for zero-shot multilingual speech synthesis in the wild, surpassing its predecessor in content consistency, speaker similarity, and prosody naturalness. Key features of CosyVoice 3 include: 1) A novel speech tokenizer to improve prosody naturalness, developed via supervised multi-task training, including automatic speech recognition, speech emotion recognition, language identification, audio event detection, and speaker analysis. 2) A new differentiable reward model for post-training applicable not only to CosyVoice 3 but also to other LLM-based speech synthesis models. 3) Dataset Size Scaling: Training data is expanded from ten thousand hours to one million hours, encompassing 9 languages and 18 Chinese dialects across various domains and text formats. 4) Model Size Scaling: Model parameters are increased from 0.5 billion to 1.5 billion, resulting in enhanced performance on our multilingual benchmark due to the larger model capacity. These advancements contribute significantly to the progress of speech synthesis in the wild. We encourage readers to listen to the demo at https://funaudiollm.github.io/cosyvoice3.

Yang Chen, Hui Wang, Shiyao Wang et al.

While voice technologies increasingly serve aging populations, current systems exhibit significant performance gaps due to inadequate training data capturing elderly-specific vocal characteristics like presbyphonia and dialectal variations. The limited data available on super-aged individuals in existing elderly speech datasets, coupled with overly simple recording styles and annotation dimensions, exacerbates this issue. To address the critical scarcity of speech data from individuals aged 75 and above, we introduce SeniorTalk, a carefully annotated Chinese spoken dialogue dataset. This dataset contains 55.53 hours of speech from 101 natural conversations involving 202 participants, ensuring a strategic balance across gender, region, and age. Through detailed annotation across multiple dimensions, it can support a wide range of speech tasks. We perform extensive experiments on speaker verification, speaker diarization, speech recognition, and speech editing tasks, offering crucial insights for the development of speech technologies targeting this age group.

Sihang Chen, Lijun Yun, Ze Liu et al.

Deep learning techniques have achieved remarkable success in the semantic segmentation of remote sensing images and in land-use change detection. Nevertheless, their real-time deployment on edge platforms remains constrained by decoder complexity. Herein, we introduce LightFormer, a lightweight decoder for time-critical tasks that involve unstructured targets, such as disaster assessment, unmanned aerial vehicle search-and-rescue, and cultural heritage monitoring. LightFormer employs a feature-fusion and refinement module built on channel processing and a learnable gating mechanism to aggregate multi-scale, multi-range information efficiently, which drastically curtails model complexity. Furthermore, we propose a spatial information selection module (SISM) that integrates long-range attention with a detail preservation branch to capture spatial dependencies across multiple scales, thereby substantially improving the recognition of unstructured targets in complex scenes. On the ISPRS Vaihingen benchmark, LightFormer attains 99.9% of GLFFNet's mIoU (83.9% vs. 84.0%) while requiring only 14.7% of its FLOPs and 15.9% of its parameters, thus achieving an excellent accuracy-efficiency trade-off. Consistent results on LoveDA, ISPRS Potsdam, RescueNet, and FloodNet further demonstrate its robustness and superior perception of unstructured objects. These findings highlight LightFormer as a practical solution for remote sensing applications where both computational economy and high-precision segmentation are imperative.

Feng Xu, Hui Wang, Yuting Huang et al.

Modeling temporal multimodal data poses significant challenges in classification tasks, particularly in capturing long-range temporal dependencies and intricate cross-modal interactions. Audiovisual data, as a representative example, is inherently characterized by strict temporal order and diverse modalities. Effectively leveraging the temporal structure is essential for understanding both intra-modal dynamics and inter-modal correlations. However, most existing approaches treat each modality independently and rely on shallow fusion strategies, which overlook temporal dependencies and hinder the model's ability to represent complex structural relationships. To address the limitation, we propose the hybrid hypergraph network (HHN), a novel framework that models temporal multimodal data via a segmentation-first, graph-later strategy. HHN splits sequences into timestamped segments as nodes in a heterogeneous graph. Intra-modal structures are captured via hyperedges guided by a maximum entropy difference criterion, enhancing node heterogeneity and structural discrimination, followed by hypergraph convolution to extract high-order dependencies. Inter-modal links are established through temporal alignment and graph attention for semantic fusion. HHN achieves state-of-the-art (SOTA) results on four multimodal datasets, demonstrating its effectiveness in complex classification tasks.

Tianqi Tu, Hui Wang, Jiangbo Pei et al.

Background: Renal chronicity indices (CI) have been identified as strong predictors of long-term outcomes in lupus nephritis (LN) patients. However, assessment by pathologists is hindered by challenges such as substantial time requirements, high interobserver variation, and susceptibility to fatigue. This study aims to develop an effective deep learning (DL) pipeline that automates the assessment of CI and provides valuable prognostic insights from a disease-specific perspective. Methods: We curated a dataset comprising 282 slides obtained from 141 patients across two independent cohorts with a complete 10-years follow-up. Our DL pipeline was developed on 60 slides (22,410 patch images) from 30 patients in the training cohort and evaluated on both an internal testing set (148 slides, 77,605 patch images) and an external testing set (74 slides, 27,522 patch images). Results: The study included two cohorts with slight demographic differences, particularly in age and hemoglobin levels. The DL pipeline showed high segmentation performance across tissue compartments and histopathologic lesions, outperforming state-of-the-art methods. The DL pipeline also demonstrated a strong correlation with pathologists in assessing CI, significantly improving interobserver agreement. Additionally, the DL pipeline enhanced prognostic accuracy, particularly in outcome prediction, when combined with clinical parameters and pathologist-assessed CIs Conclusions: The DL pipeline demonstrated accuracy and efficiency in assessing CI in LN, showing promise in improving interobserver agreement among pathologists. It also exhibited significant value in prognostic analysis and enhancing outcome prediction in LN patients, offering a valuable tool for clinical decision-making.

Brahim Driss, Jérôme Arjonilla, Hui Wang et al.

In recent years, much progress has been made in computer Go and most of the results have been obtained thanks to search algorithms (Monte Carlo Tree Search) and Deep Reinforcement Learning (DRL). In this paper, we propose to use and analyze the latest algorithms that use search and DRL (AlphaZero and Descent algorithms) to automatically learn to play an extended version of the game of Go with more than two players. We show that using search and DRL we were able to improve the level of play, even though there are more than two players.

Ji Huang, Hui Wang

The main challenge for small object detection algorithms is to ensure accuracy while pursuing real-time performance. The RT-DETR model performs well in real-time object detection, but performs poorly in small object detection accuracy. In order to compensate for the shortcomings of the RT-DETR model in small object detection, two key improvements are proposed in this study. Firstly, The RT-DETR utilises a Transformer that receives input solely from the final layer of Backbone features. This means that the Transformer's input only receives semantic information from the highest level of abstraction in the Deep Network, and ignores detailed information such as edges, texture or color gradients that are critical to the location of small objects at lower levels of abstraction. Including only deep features can introduce additional background noise. This can have a negative impact on the accuracy of small object detection. To address this issue, we propose the fine-grained path augmentation method. This method helps to locate small objects more accurately by providing detailed information to the deep network. So, the input to the transformer contains both semantic and detailed information. Secondly, In RT-DETR, the decoder takes feature maps of different levels as input after concatenating them with equal weight. However, this operation is not effective in dealing with the complex relationship of multi-scale information captured by feature maps of different sizes. Therefore, we propose an adaptive feature fusion algorithm that assigns learnable parameters to each feature map from different levels. This allows the model to adaptively fuse feature maps from different levels and effectively integrate feature information from different scales. This enhances the model's ability to capture object features at different scales, thereby improving the accuracy of detecting small objects.

Gyeong-Geon Lee, Lehong Shi, Ehsan Latif et al.

This paper presents a comprehensive examination of how multimodal artificial intelligence (AI) approaches are paving the way towards the realization of Artificial General Intelligence (AGI) in educational contexts. It scrutinizes the evolution and integration of AI in educational systems, emphasizing the crucial role of multimodality, which encompasses auditory, visual, kinesthetic, and linguistic modes of learning. This research delves deeply into the key facets of AGI, including cognitive frameworks, advanced knowledge representation, adaptive learning mechanisms, strategic planning, sophisticated language processing, and the integration of diverse multimodal data sources. It critically assesses AGI's transformative potential in reshaping educational paradigms, focusing on enhancing teaching and learning effectiveness, filling gaps in existing methodologies, and addressing ethical considerations and responsible usage of AGI in educational settings. The paper also discusses the implications of multimodal AI's role in education, offering insights into future directions and challenges in AGI development. This exploration aims to provide a nuanced understanding of the intersection between AI, multimodality, and education, setting a foundation for future research and development in AGI.

Sicen Liu, Xiaolong Wang, Yongshuai Hou et al.

As two important textual modalities in electronic health records (EHR), both structured data (clinical codes) and unstructured data (clinical narratives) have recently been increasingly applied to the healthcare domain. Most existing EHR-oriented studies, however, either focus on a particular modality or integrate data from different modalities in a straightforward manner, which usually treats structured and unstructured data as two independent sources of information about patient admission and ignore the intrinsic interactions between them. In fact, the two modalities are documented during the same encounter where structured data inform the documentation of unstructured data and vice versa. In this paper, we proposed a Medical Multimodal Pre-trained Language Model, named MedM-PLM, to learn enhanced EHR representations over structured and unstructured data and explore the interaction of two modalities. In MedM-PLM, two Transformer-based neural network components are firstly adopted to learn representative characteristics from each modality. A cross-modal module is then introduced to model their interactions. We pre-trained MedM-PLM on the MIMIC-III dataset and verified the effectiveness of the model on three downstream clinical tasks, i.e., medication recommendation, 30-day readmission prediction and ICD coding. Extensive experiments demonstrate the power of MedM-PLM compared with state-of-the-art methods. Further analyses and visualizations show the robustness of our model, which could potentially provide more comprehensive interpretations for clinical decision-making.

Dongran Yu, Bo Yang, Dayou Liu et al.

In recent years, neural systems have demonstrated highly effective learning ability and superior perception intelligence. However, they have been found to lack effective reasoning and cognitive ability. On the other hand, symbolic systems exhibit exceptional cognitive intelligence but suffer from poor learning capabilities when compared to neural systems. Recognizing the advantages and disadvantages of both methodologies, an ideal solution emerges: combining neural systems and symbolic systems to create neural-symbolic learning systems that possess powerful perception and cognition. The purpose of this paper is to survey the advancements in neural-symbolic learning systems from four distinct perspectives: challenges, methods, applications, and future directions. By doing so, this research aims to propel this emerging field forward, offering researchers a comprehensive and holistic overview. This overview will not only highlight the current state-of-the-art but also identify promising avenues for future research.

Hui Wang, Kun Zhou, Wayne Xin Zhao et al.

Due to the flexibility in modelling data heterogeneity, heterogeneous information network (HIN) has been adopted to characterize complex and heterogeneous auxiliary data in top-$N$ recommender systems, called \emph{HIN-based recommendation}. HIN characterizes complex, heterogeneous data relations, containing a variety of information that may not be related to the recommendation task. Therefore, it is challenging to effectively leverage useful information from HINs for improving the recommendation performance. To address the above issue, we propose a Curriculum pre-training based HEterogeneous Subgraph Transformer (called \emph{CHEST}) with new \emph{data characterization}, \emph{representation model} and \emph{learning algorithm}. Specifically, we consider extracting useful information from HIN to compose the interaction-specific heterogeneous subgraph, containing both sufficient and relevant context information for recommendation. Then we capture the rich semantics (\eg graph structure and path semantics) within the subgraph via a heterogeneous subgraph Transformer, where we encode the subgraph with multi-slot sequence representations. Besides, we design a curriculum pre-training strategy to provide an elementary-to-advanced learning process, by which we smoothly transfer basic semantics in HIN for modeling user-item interaction relation. Extensive experiments conducted on three real-world datasets demonstrate the superiority of our proposed method over a number of competitive baselines, especially when only limited training data is available.

Hui Wang, Zongsheng Yue, Qian Zhao et al.

Blind image deblurring is an important yet very challenging problem in low-level vision. Traditional optimization based methods generally formulate this task as a maximum-a-posteriori estimation or variational inference problem, whose performance highly relies on the handcraft priors for both the latent image and the blur kernel. In contrast, recent deep learning methods generally learn, from a large collection of training images, deep neural networks (DNNs) directly mapping the blurry image to the clean one or to the blur kernel, paying less attention to the physical degradation process of the blurry image. In this paper, we present a deep variational Bayesian framework for blind image deblurring. Under this framework, the posterior of the latent clean image and blur kernel can be jointly estimated in an amortized inference fashion with DNNs, and the involved inference DNNs can be trained by fully considering the physical blur model, together with the supervision of data driven priors for the clean image and blur kernel, which is naturally led to by the evidence lower bound objective. Comprehensive experiments are conducted to substantiate the effectiveness of the proposed framework. The results show that it can not only achieve a promising performance with relatively simple networks, but also enhance the performance of existing DNNs for deblurring.

Hui Wang, Mike Preuss, Aske Plaat

AlphaZero has achieved impressive performance in deep reinforcement learning by utilizing an architecture that combines search and training of a neural network in self-play. Many researchers are looking for ways to reproduce and improve results for other games/tasks. However, the architecture is designed to learn from scratch, tabula rasa, accepting a cold-start problem in self-play. Recently, a warm-start enhancement method for Monte Carlo Tree Search was proposed to improve the self-play starting phase. It employs a fixed parameter $I^\prime$ to control the warm-start length. Improved performance was reported in small board games. In this paper we present results with an adaptive switch method. Experiments show that our approach works better than the fixed $I^\prime$, especially for "deep," tactical, games (Othello and Connect Four). We conjecture that the adaptive value for $I^\prime$ is also influenced by the size of the game, and that on average $I^\prime$ will increase with game size. We conclude that AlphaZero-like deep reinforcement learning benefits from adaptive rollout based warm-start, as Rapid Action Value Estimate did for rollout-based reinforcement learning 15 years ago.

Wei Zeng, Xiaozhe Ren, Teng Su et al.

Large-scale Pretrained Language Models (PLMs) have become the new paradigm for Natural Language Processing (NLP). PLMs with hundreds of billions parameters such as GPT-3 have demonstrated strong performances on natural language understanding and generation with \textit{few-shot in-context} learning. In this work, we present our practice on training large-scale autoregressive language models named PanGu-$α$, with up to 200 billion parameters. PanGu-$α$ is developed under the MindSpore and trained on a cluster of 2048 Ascend 910 AI processors. The training parallelism strategy is implemented based on MindSpore Auto-parallel, which composes five parallelism dimensions to scale the training task to 2048 processors efficiently, including data parallelism, op-level model parallelism, pipeline model parallelism, optimizer model parallelism and rematerialization. To enhance the generalization ability of PanGu-$α$, we collect 1.1TB high-quality Chinese data from a wide range of domains to pretrain the model. We empirically test the generation ability of PanGu-$α$ in various scenarios including text summarization, question answering, dialogue generation, etc. Moreover, we investigate the effect of model scales on the few-shot performances across a broad range of Chinese NLP tasks. The experimental results demonstrate the superior capabilities of PanGu-$α$ in performing various tasks under few-shot or zero-shot settings.

Hui Wang, Jian Tian, Songyuan Li et al.

Unsupervised domain adaptation (UDA) typically carries out knowledge transfer from a label-rich source domain to an unlabeled target domain by adversarial learning. In principle, existing UDA approaches mainly focus on the global distribution alignment between domains while ignoring the intrinsic local distribution properties. Motivated by this observation, we propose an end-to-end structure-conditioned adversarial learning scheme (SCAL) that is able to preserve the intra-class compactness during domain distribution alignment. By using local structures as structure-aware conditions, the proposed scheme is implemented in a structure-conditioned adversarial learning pipeline. The above learning procedure is iteratively performed by alternating between local structures establishment and structure-conditioned adversarial learning. Experimental results demonstrate the effectiveness of the proposed scheme in UDA scenarios.

Hanbin Zhao, Hui Wang, Yongjian Fu et al.

With the memory-resource-limited constraints, class-incremental learning (CIL) usually suffers from the "catastrophic forgetting" problem when updating the joint classification model on the arrival of newly added classes. To cope with the forgetting problem, many CIL methods transfer the knowledge of old classes by preserving some exemplar samples into the size-constrained memory buffer. To utilize the memory buffer more efficiently, we propose to keep more auxiliary low-fidelity exemplar samples rather than the original real high-fidelity exemplar samples. Such a memory-efficient exemplar preserving scheme makes the old-class knowledge transfer more effective. However, the low-fidelity exemplar samples are often distributed in a different domain away from that of the original exemplar samples, that is, a domain shift. To alleviate this problem, we propose a duplet learning scheme that seeks to construct domain-compatible feature extractors and classifiers, which greatly narrows down the above domain gap. As a result, these low-fidelity auxiliary exemplar samples have the ability to moderately replace the original exemplar samples with a lower memory cost. In addition, we present a robust classifier adaptation scheme, which further refines the biased classifier (learned with the samples containing distillation label knowledge about old classes) with the help of the samples of pure true class labels. Experimental results demonstrate the effectiveness of this work against the state-of-the-art approaches.

Hanbin Zhao, Hao Zeng, Xin Qin et al.

As an important and challenging problem, multi-domain learning (MDL) typically seeks for a set of effective lightweight domain-specific adapter modules plugged into a common domain-agnostic network. Usually, existing ways of adapter plugging and structure design are handcrafted and fixed for all domains before model learning, resulting in the learning inflexibility and computational intensiveness. With this motivation, we propose to learn a data-driven adapter plugging strategy with Neural Architecture Search (NAS), which automatically determines where to plug for those adapter modules. Furthermore, we propose a NAS-adapter module for adapter structure design in a NAS-driven learning scheme, which automatically discovers effective adapter module structures for different domains. Experimental results demonstrate the effectiveness of our MDL model against existing approaches under the conditions of comparable performance.

Hui Wang, Mike Preuss, Michael Emmerich et al.

Morpion Solitaire is a popular single player game, performed with paper and pencil. Due to its large state space (on the order of the game of Go) traditional search algorithms, such as MCTS, have not been able to find good solutions. A later algorithm, Nested Rollout Policy Adaptation, was able to find a new record of 82 steps, albeit with large computational resources. After achieving this record, to the best of our knowledge, there has been no further progress reported, for about a decade. In this paper we take the recent impressive performance of deep self-learning reinforcement learning approaches from AlphaGo/AlphaZero as inspiration to design a searcher for Morpion Solitaire. A challenge of Morpion Solitaire is that the state space is sparse, there are few win/loss signals. Instead, we use an approach known as ranked reward to create a reinforcement learning self-play framework for Morpion Solitaire. This enables us to find medium-quality solutions with reasonable computational effort. Our record is a 67 steps solution, which is very close to the human best (68) without any other adaptation to the problem than using ranked reward. We list many further avenues for potential improvement.

Hui Wang, Michael Emmerich, Mike Preuss et al.

The landmark achievements of AlphaGo Zero have created great research interest into self-play in reinforcement learning. In self-play, Monte Carlo Tree Search is used to train a deep neural network, that is then used in tree searches. Training itself is governed by many hyperparameters.There has been surprisingly little research on design choices for hyper-parameter values and loss-functions, presumably because of the prohibitive computational cost to explore the parameter space. In this paper, we investigate 12 hyper-parameters in an AlphaZero-like self-play algorithm and evaluate how these parameters contribute to training. We use small games, to achieve meaningful exploration with moderate computational effort. The experimental results show that training is highly sensitive to hyper-parameter choices. Through multi-objective analysis we identify 4 important hyper-parameters to further assess. To start, we find surprising results where too much training can sometimes lead to lower performance. Our main result is that the number of self-play iterations subsumes MCTS-search simulations, game-episodes, and training epochs. The intuition is that these three increase together as self-play iterations increase, and that increasing them individually is sub-optimal. A consequence of our experiments is a direct recommendation for setting hyper-parameter values in self-play: the overarching outer-loop of self-play iterations should be maximized, in favor of the three inner-loop hyper-parameters, which should be set at lower values. A secondary result of our experiments concerns the choice of optimization goals, for which we also provide recommendations.

Chunli Qin, Demin Yao, Han Zhuang et al.

Accurate identification and localization of the vertebrae in CT scans is a critical and standard preprocessing step for clinical spinal diagnosis and treatment. Existing methods are mainly based on the integration of multiple neural networks, and most of them use the Gaussian heat map to locate the vertebrae's centroid. However, the process of obtaining the vertebrae's centroid coordinates using heat maps is non-differentiable, so it is impossible to train the network to label the vertebrae directly. Therefore, for end-to-end differential training of vertebra coordinates on CT scans, a robust and accurate automatic vertebral labeling algorithm is proposed in this study. Firstly, a novel residual-based multi-label classification and localization network is developed, which can capture multi-scale features, but also utilize the residual module and skip connection to fuse the multi-level features. Secondly, to solve the problem that the process of finding coordinates is non-differentiable and the spatial structure is not destructible, integral regression module is used in the localization network. It combines the advantages of heat map representation and direct regression coordinates to achieve end-to-end training, and can be compatible with any key point detection methods of medical image based on heat map. Finally, multi-label classification of vertebrae is carried out, which use bidirectional long short term memory (Bi-LSTM) to enhance the learning of long contextual information to improve the classification performance. The proposed method is evaluated on a challenging dataset and the results are significantly better than the state-of-the-art methods (mean localization error <3mm).

Lianbo Ma, Peng Sun, Zhiwei Lin et al.

Learning knowledge graph embedding from an existing knowledge graph is very important to knowledge graph completion. For a fact $(h,r,t)$ with the head entity $h$ having a relation $r$ with the tail entity $t$, the current approaches aim to learn low dimensional representations $(\mathbf{h},\mathbf{r},\mathbf{t})$, each of which corresponds to the elements in $(h, r, t)$, respectively. As $(\mathbf{h},\mathbf{r},\mathbf{t})$ is learned from the existing facts within a knowledge graph, these representations can not be used to detect unknown facts (if the entities or relations never occur in the knowledge graph). This paper proposes a new approach called TransW, aiming to go beyond the current work by composing knowledge graph embeddings using word embeddings. Given the fact that an entity or a relation contains one or more words (quite often), it is sensible to learn a mapping function from word embedding spaces to knowledge embedding spaces, which shows how entities are constructed using human words. More importantly, composing knowledge embeddings using word embeddings makes it possible to deal with the emerging new facts (either new entities or relations). Experimental results using three public datasets show the consistency and outperformance of the proposed TransW.

Wan-Lei Zhao, Hui Wang, Peng-Cheng Lin et al.

k-nearest neighbor graph is a fundamental data structure in many disciplines such as information retrieval, data-mining, pattern recognition, and machine learning, etc. In the literature, considerable research has been focusing on how to efficiently build an approximate k-nearest neighbor graph (k-NN graph) for a fixed dataset. Unfortunately, a closely related issue of how to merge two existing k-NN graphs has been overlooked. In this paper, we address the issue of k-NN graph merging in two different scenarios. In the first scenario, a symmetric merge algorithm is proposed to combine two approximate k-NN graphs. The algorithm facilitates large-scale processing by the efficient merging of k-NN graphs that are produced in parallel. In the second scenario, a joint merge algorithm is proposed to expand an existing k-NN graph with a raw dataset. The algorithm enables the incremental construction of a hierarchical approximate k-NN graph. Superior performance is attained when leveraging the hierarchy for NN search of various data types, dimensionality, and distance measures.

Wei Qionghua, Wang Hui, Wei Qiang

Recently, great progress has been made in virtual reality(VR) research and application. However, virtual reality faces a big problem since its appearance, i.e. discomfort (nausea, stomach awareness, etc). Discomfort can be relieved by increasing hardware (sensor, cpu and display) speed. But this will increase cost. This paper gives another low cost solution. The phenomenon of cybersickness is explained with the control theory: discomfort arises if feedback scene differs from expectation, so it can be relieved by disturbing feedback loop in human brain. A hardware platform is build to test this explanation. The VR display on a Samsung S6 is blurred while head movement is detected. The effect is evaluated by comparing responses to the Simulated Sickness Questionnaire (SSQ) between a control and experimental condition. Experimental results show that the new method can ease discomfort remarkably with little extra cost. As a result, VR may be used more widely in teaching (like foreign language, medicine). It's also reasonable to expect likewise merits in other VR applications.

Raymond Bond, Ansgar Koene, Alan Dix et al.

Many industries are now investing heavily in data science and automation to replace manual tasks and/or to help with decision making, especially in the realm of leveraging computer vision to automate many monitoring, inspection, and surveillance tasks. This has resulted in the emergence of the 'data scientist' who is conversant in statistical thinking, machine learning (ML), computer vision, and computer programming. However, as ML becomes more accessible to the general public and more aspects of ML become automated, applications leveraging computer vision are increasingly being created by non-experts with less opportunity for regulatory oversight. This points to the overall need for more educated responsibility for these lay-users of usable ML tools in order to mitigate potentially unethical ramifications. In this paper, we undertake a SWOT analysis to study the strengths, weaknesses, opportunities, and threats of building usable ML tools for mass adoption for important areas leveraging ML such as computer vision. The paper proposes a set of data science literacy criteria for educating and supporting lay-users in the responsible development and deployment of ML applications.

Bo Zhang, Boxiang Dong, Hui Wang

Spurred by the development of cloud computing, there has been considerable recent interest in the Database-as-a-Service (DaaS) paradigm. Users lacking in expertise or computational resources can outsource their data and database management needs to a third-party service provider. Outsourcing, however, raises an important issue of result integrity: how can the client verify with lightweight overhead that the query results returned by the service provider are correct (i.e., the same as the results of query execution locally)? This survey focuses on categorizing and reviewing the progress on the current approaches for result integrity of SQL query evaluation in the DaaS model. The survey also includes some potential future research directions for result integrity verification of the outsourced computations.

Bo Zhang, Boxiang Dong, Hui Wang

Spurred by developments such as cloud computing, there are increasing efforts for outsourcing of data management. A company (data owner) who lacks expertise and comptational resources can outsource his data to a third-party service provider (server), who provides storage and query evaluation on the outsourced data as the services. One of the security concerns of the outsourcing paradigm is the integrity of the returned query results on the outsourced data. In this paper, we consider the outsourcing of probabilistic databases, on which query evaluation is of high complexity. A dishonest server may return cheap (and incorrect) query answers, hoping that the client who has weak computational power cannot catch the incorrect results. To address this issue, we design efficient integrity verification methods for both all-answer and top-k query evaluation on outsourced probabilistic databases. Our empirical results demonstrate the effectiveness and efficiency of our verification methods.

Ivo Düntsch, Günther Gediga, Hui Wang

In this exploratory article, we draw attention to the common formal ground among various estimators such as the belief functions of evidence theory and their relatives, approximation quality of rough set theory, and contextual probability. The unifying concept will be a general filter function composed of a basic probability and a weighting which varies according to the problem at hand. To compare the various filter functions we conclude with a simulation study with an example from the area of item response theory.

Xin Wei, Hui Wang, Bryan Scotney et al.

Face recognition has achieved great progress owing to the fast development of the deep neural network in the past a few years. As an important part of deep neural networks, a number of the loss functions have been proposed which significantly improve the state-of-the-art methods. In this paper, we proposed a new loss function called Minimum Margin Loss (MML) which aims at enlarging the margin of those overclose class centre pairs so as to enhance the discriminative ability of the deep features. MML supervises the training process together with the Softmax Loss and the Centre Loss, and also makes up the defect of Softmax + Centre Loss. The experimental results on MegaFace, LFW and YTF datasets show that the proposed method achieves the state-of-the-art performance, which demonstrates the effectiveness of the proposed MML.

Wan-Lei Zhao, Hui Wang, Chong-Wah Ngo

Nearest neighbor search and k-nearest neighbor graph construction are two fundamental issues arise from many disciplines such as multimedia information retrieval, data-mining and machine learning. They become more and more imminent given the big data emerge in various fields in recent years. In this paper, a simple but effective solution both for approximate k-nearest neighbor search and approximate k-nearest neighbor graph construction is presented. These two issues are addressed jointly in our solution. On the one hand, the approximate k-nearest neighbor graph construction is treated as a search task. Each sample along with its k-nearest neighbors are joined into the k-nearest neighbor graph by performing the nearest neighbor search sequentially on the graph under construction. On the other hand, the built k-nearest neighbor graph is used to support k-nearest neighbor search. Since the graph is built online, the dynamic update on the graph, which is not possible from most of the existing solutions, is supported. This solution is feasible for various distance measures. Its effectiveness both as k-nearest neighbor construction and k-nearest neighbor search approaches is verified across different types of data in different scales, various dimensions and under different metrics.

Qin Zhang, Hui Wang, Junyu Dong et al.

This letter adopts long short-term memory(LSTM) to predict sea surface temperature(SST), which is the first attempt, to our knowledge, to use recurrent neural network to solve the problem of SST prediction, and to make one week and one month daily prediction. We formulate the SST prediction problem as a time series regression problem. LSTM is a special kind of recurrent neural network, which introduces gate mechanism into vanilla RNN to prevent the vanished or exploding gradient problem. It has strong ability to model the temporal relationship of time series data and can handle the long-term dependency problem well. The proposed network architecture is composed of two kinds of layers: LSTM layer and full-connected dense layer. LSTM layer is utilized to model the time series relationship. Full-connected layer is utilized to map the output of LSTM layer to a final prediction. We explore the optimal setting of this architecture by experiments and report the accuracy of coastal seas of China to confirm the effectiveness of the proposed method. In addition, we also show its online updated characteristics.

Boxiang Dong, Zhengzhang Chen, Hui Wang et al.

Intrusion detection system (IDS) is an important part of enterprise security system architecture. In particular, anomaly-based IDS has been widely applied to detect abnormal process behaviors that deviate from the majority. However, such abnormal behavior usually consists of a series of low-level heterogeneous events. The gap between the low-level events and the high-level abnormal behaviors makes it hard to infer which single events are related to the real abnormal activities, especially considering that there are massive "noisy" low-level events happening in between. Hence, the existing work that focus on detecting single entities/events can hardly achieve high detection accuracy. Different from previous work, we design and implement GID, an efficient graph-based intrusion detection technique that can identify abnormal event sequences from a massive heterogeneous process traces with high accuracy. GID first builds a compact graph structure to capture the interactions between different system entities. The suspiciousness or anomaly score of process paths is then measured by leveraging random walk technique to the constructed acyclic directed graph. To eliminate the score bias from the path length, the Box-Cox power transformation based approach is introduced to normalize the anomaly scores so that the scores of paths of different lengths have the same distribution. The efficiency of suspicious path discovery is further improved by the proposed optimization scheme. We fully implement our GID algorithm and deploy it into a real enterprise security system, and it greatly helps detect the advanced threats, and optimize the incident response. Executing GID on system monitoring datasets showing that GID is efficient (about 2 million records per minute) and accurate (higher than 80% in terms of detection rate).

Boxiang Dong, Hui Wang

Cloud computing enables the outsourcing of big data analytics, where a third party server is responsible for data storage and processing. In this paper, we consider the outsourcing model that provides string similarity search as the service. In particular, given a similarity search query, the service provider returns all strings from the outsourced dataset that are similar to the query string. A major security concern of the outsourcing paradigm is to authenticate whether the service provider returns sound and complete search results. In this paper, we design AutoS3, an authentication mechanism of outsourced string similarity search. The key idea of AutoS3 is that the server returns a verification object VO to prove the result correctness. First, we design an authenticated string indexing structure named MBtree for VO construction. Second, we design two lightweight authentication methods named VS2 and EVS2 that can catch the service provider various cheating behaviors with cheap verification cost. Moreover, we generalize our solution for top k string similarity search. We perform an extensive set of experiment results on real world datasets to demonstrate the efficiency of our approach.

Prashanti Manda, Fiona McCarthy, Bindu Nanduri et al.

Community annotation of biological entities with concepts from multiple bio-ontologies has created large and growing repositories of ontology-based annotation data with embedded implicit relationships among orthogonal ontologies. Development of efficient data mining methods and metrics to mine and assess the quality of the mined relationships has not kept pace with the growth of annotation data. In this study, we present a data mining method that uses ontology-guided generalization to discover relationships across ontologies along with a new interestingness metric based on information theory. We apply our data mining algorithm and interestingness measures to datasets from the Gene Expression Database at the Mouse Genome Informatics as a preliminary proof of concept to mine relationships between developmental stages in the mouse anatomy ontology and Gene Ontology concepts (biological process, molecular function and cellular component). In addition, we present a comparison of our interestingness metric to four existing metrics. Ontology-based annotation datasets provide a valuable resource for discovery of relationships across ontologies. The use of efficient data mining methods and appropriate interestingness metrics enables the identification of high quality relationships.