Huaimin Wang

Ruiqing Sun, Sen Yang, Dawei Feng et al.

Offline multi-objective optimization (Offline MOO) aims to discover novel Pareto-optimal designs based on static datasets without expensive environment interactions. While recent generative methods have achieved notable success, they predominantly rely on external surrogate models. This dependency introduces significant computational overhead, suffers from deceptive evaluations, and deviates from the prevailing paradigm of jointly training mainstream generative models with conditions. To address these bottlenecks, we propose ParetoPilot, a novel zero-surrogate diffusion framework for offline MOO. ParetoPilot fully leverages the conditional priors inherently embedded within pre-trained diffusion models. At its core, the framework introduces the Infer-Perturb-Guide (IPG) engine, which is seamlessly interleaved within the unconditional denoising steps of the reverse generation process. First, it implicitly infers the instantaneous objective direction by matching conditional and unconditional noise predictions. Next, it mathematically orthogonalizes a parallel gravity field for strict convergence and an edgeness-aware repulsive force for mutual diversity, creating a dynamically annealed perturbation vector. Finally, this perturbed target seamlessly steers the generation process via standard Classifier-Free Guidance (CFG). Extensive experiments across 51 tasks demonstrate that ParetoPilot outperforms 14 state-of-the-art surrogate-based and inverse generative baselines. By eliminating auxiliary proxy training, our approach preserves data privacy while achieving hypervolume improvement and robust Pareto front coverage.

Shiqiang Zhu, Ting Yu, Tao Xu et al.

Computing is a critical driving force in the development of human civilization. In recent years, we have witnessed the emergence of intelligent computing, a new computing paradigm that is reshaping traditional computing and promoting digital revolution in the era of big data, artificial intelligence and internet-of-things with new computing theories, architectures, methods, systems, and applications. Intelligent computing has greatly broadened the scope of computing, extending it from traditional computing on data to increasingly diverse computing paradigms such as perceptual intelligence, cognitive intelligence, autonomous intelligence, and human-computer fusion intelligence. Intelligence and computing have undergone paths of different evolution and development for a long time but have become increasingly intertwined in recent years: intelligent computing is not only intelligence-oriented but also intelligence-driven. Such cross-fertilization has prompted the emergence and rapid advancement of intelligent computing. Intelligent computing is still in its infancy and an abundance of innovations in the theories, systems, and applications of intelligent computing are expected to occur soon. We present the first comprehensive survey of literature on intelligent computing, covering its theory fundamentals, the technological fusion of intelligence and computing, important applications, challenges, and future perspectives. We believe that this survey is highly timely and will provide a comprehensive reference and cast valuable insights into intelligent computing for academic and industrial researchers and practitioners.

Yuanzhao Zhai, Tingkai Yang, Kele Xu et al.

Agents significantly enhance the capabilities of standalone Large Language Models (LLMs) by perceiving environments, making decisions, and executing actions. However, LLM agents still face challenges in tasks that require multiple decision-making steps. Estimating the value of actions in specific tasks is difficult when intermediate actions are neither appropriately rewarded nor penalized. In this paper, we propose leveraging a task-relevant Q-value model to guide action selection. Specifically, we first collect decision-making trajectories annotated with step-level Q values via Monte Carlo Tree Search (MCTS) and construct preference data. We then use another LLM to fit these preferences through step-level Direct Policy Optimization (DPO), which serves as the Q-value model. During inference, at each decision-making step, LLM agents select the action with the highest Q value before interacting with the environment. We apply our method to various open-source and API-based LLM agents, demonstrating that Q-value models significantly improve their performance. Notably, the performance of the agent built with Phi-3-mini-4k-instruct improved by 103% on WebShop and 75% on HotPotQA when enhanced with Q-value models, even surpassing GPT-4o-mini. Additionally, Q-value models offer several advantages, such as generalization to different LLM agents and seamless integration with existing prompting strategies.

Boqing Zhu, Kele Xu, Changjian Wang et al.

We present an approach to learn voice-face representations from the talking face videos, without any identity labels. Previous works employ cross-modal instance discrimination tasks to establish the correlation of voice and face. These methods neglect the semantic content of different videos, introducing false-negative pairs as training noise. Furthermore, the positive pairs are constructed based on the natural correlation between audio clips and visual frames. However, this correlation might be weak or inaccurate in a large amount of real-world data, which leads to deviating positives into the contrastive paradigm. To address these issues, we propose the cross-modal prototype contrastive learning (CMPC), which takes advantage of contrastive methods and resists adverse effects of false negatives and deviate positives. On one hand, CMPC could learn the intra-class invariance by constructing semantic-wise positives via unsupervised clustering in different modalities. On the other hand, by comparing the similarities of cross-modal instances from that of cross-modal prototypes, we dynamically recalibrate the unlearnable instances' contribution to overall loss. Experiments show that the proposed approach outperforms state-of-the-art unsupervised methods on various voice-face association evaluation protocols. Additionally, in the low-shot supervision setting, our method also has a significant improvement compared to previous instance-wise contrastive learning.

Chao Chen, Zijian Gao, Kele Xu et al.

To handle the sparsity of the extrinsic rewards in reinforcement learning, researchers have proposed intrinsic reward which enables the agent to learn the skills that might come in handy for pursuing the rewards in the future, such as encouraging the agent to visit novel states. However, the intrinsic reward can be noisy due to the undesirable environment's stochasticity and directly applying the noisy value predictions to supervise the policy is detrimental to improve the learning performance and efficiency. Moreover, many previous studies employ $\ell^2$ norm or variance to measure the exploration novelty, which will amplify the noise due to the square operation. In this paper, we address aforementioned challenges by proposing a novel curiosity leveraging the nuclear norm maximization (NNM), which can quantify the novelty of exploring the environment more accurately while providing high-tolerance to the noise and outliers. We conduct extensive experiments across a variety of benchmark environments and the results suggest that NNM can provide state-of-the-art performance compared with previous curiosity methods. On 26 Atari games subset, when trained with only intrinsic reward, NNM achieves a human-normalized score of 1.09, which doubles that of competitive intrinsic rewards-based approaches. Our code will be released publicly to enhance the reproducibility.

Ming Feng, Kele Xu, Nanhui Wu et al.

Despite remarkable efforts been made, the classification of gigapixels whole-slide image (WSI) is severely restrained from either the constrained computing resources for the whole slides, or limited utilizing of the knowledge from different scales. Moreover, most of the previous attempts lacked of the ability of uncertainty estimation. Generally, the pathologists often jointly analyze WSI from the different magnifications. If the pathologists are uncertain by using single magnification, then they will change the magnification repeatedly to discover various features of the tissues. Motivated by the diagnose process of the pathologists, in this paper, we propose a trusted multi-scale classification framework for the WSI. Leveraging the Vision Transformer as the backbone for multi branches, our framework can jointly classification modeling, estimating the uncertainty of each magnification of a microscope and integrate the evidence from different magnification. Moreover, to exploit discriminative patches from WSIs and reduce the requirement for computation resources, we propose a novel patch selection schema using attention rollout and non-maximum suppression. To empirically investigate the effectiveness of our approach, empirical experiments are conducted on our WSI classification tasks, using two benchmark databases. The obtained results suggest that the trusted framework can significantly improve the WSI classification performance compared with the state-of-the-art methods.

Zijian Gao, Kele Xu, Yuanzhao Zhai et al.

Under sparse extrinsic reward settings, reinforcement learning has remained challenging, despite surging interests in this field. Previous attempts suggest that intrinsic reward can alleviate the issue caused by sparsity. In this article, we present a novel intrinsic reward that is inspired by human learning, as humans evaluate curiosity by comparing current observations with historical knowledge. Our method involves training a self-supervised prediction model, saving snapshots of the model parameters, and using nuclear norm to evaluate the temporal inconsistency between the predictions of different snapshots as intrinsic rewards. We also propose a variational weighting mechanism to assign weight to different snapshots in an adaptive manner. Our experimental results on various benchmark environments demonstrate the efficacy of our method, which outperforms other intrinsic reward-based methods without additional training costs and with higher noise tolerance. This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.

Yi Xiong, Liang Xiong, Xiaohong Ji et al.

Molecular property optimization is central to drug discovery, yet many deep learning methods rely on black-box scoring and offer limited control over scaffold preservation, often producing unstable or biologically implausible edits. While large language models (LLMs) are promising molecular generators, optimization remains constrained by the lack of chemistry-grounded preference supervision and principled data curation. We introduce \textbf{Scaffold-Conditioned Preference Triplets (SCPT)}, a pipeline that constructs similarity-constrained triplets $\langle\text{scaffold}, \text{better}, \text{worse}\rangle$ via scaffold alignment and chemistry-driven filters for validity, synthesizability, and meaningful property gains. Using these preferences, we align a pretrained molecular LLM as a conditional editor, enabling property-improving edits that retain the scaffold. Across single- and multi-objective benchmarks, SCPT improves optimization success and property gains while maintaining higher scaffold similarity than competitive baselines. Compared with representative non-LLM molecular optimization methods, SCPT-trained LLMs are better suited to scaffold-constrained and multi-objective optimization. In addition, models trained on single-property and two-property supervision generalize effectively to three-property tasks, indicating promising extrapolative generalization under limited higher-order supervision. SCPT also provides controllable data-construction knobs that yield a predictable similarity-gain frontier, enabling systematic adaptation to diverse optimization regimes.

Zijian Gao, Wangwang Jia, Xingxing Zhang et al.

Multimodal Continual Instruction Tuning (MCIT) is essential for sequential task adaptation of Multimodal Large Language Models (MLLMs) but is severely restricted by catastrophic forgetting. While existing literature focuses on the reasoning language backbone, in this work, we expose a critical yet neglected dual-forgetting phenomenon across both perception drift in Cross-modal Projection Space and reasoning collapse in Low-rank Parameter Space. To resolve this, we present \textbf{MAny} (\textbf{M}erge \textbf{Any}thing), a framework that merges task-specific knowledge through \textbf{C}ross-modal \textbf{P}rojection \textbf{M}erging (\textbf{CPM}) and \textbf{L}ow-rank \textbf{P}arameter \textbf{M}erging (\textbf{LPM}). Specifically, CPM recovers perceptual alignment by adaptively merging cross-modal visual representations via visual-prototype guidance, ensuring accurate feature recovery during inference. Simultaneously, LPM eliminates mutual interference among task-specific low-rank modules by recursively merging low-rank weight matrices. By leveraging recursive least squares, LPM provides a closed-form solution that mathematically guarantees an optimal fusion trajectory for reasoning stability. Notably, MAny operates as a training-free paradigm that achieves knowledge merging via efficient CPU-based algebraic operations, eliminating additional gradient-based optimization beyond initial tuning. Our extensive evaluations confirm the superior performance and robustness of MAny across multiple MLLMs and benchmarks. Specifically, on the UCIT benchmark, MAny achieves significant leads of up to 8.57\% and 2.85\% in final average accuracy over state-of-the-art methods across two different MLLMs, respectively.

Ruiqing Sun, Dawei Feng, Sen Yang et al.

In 3D molecular discovery, optimizing conflicting physicochemical properties while strictly adhering to complex structural constraints constitutes a Constrained Multi-Objective Optimization Problem (CMOP). Solving this remains highly challenging: applying traditional Evolutionary Algorithm (EA) operators directly to 3D coordinates destroys chemical validity, whereas valid 3D diffusion models act as rigid generators unable to adapt to novel objectives without retraining. Moreover, employing traditional EA frameworks causes a severe loss of structural diversity, ultimately impairing algorithmic convergence. To overcome these challenges, we propose the Evolutionary-Guided Diffusion (EGD) operator, which executes crossover and mutation exclusively within the continuous noise space at an appropriate noise intensity. EGD enables topological hybridization while leveraging a pre-trained denoising network to project intermediate states back onto the valid chemical manifold. To tackle Multi-Objective Problems (MOPs), we introduce a Structure-Aware Environmental Selection (SAES) mechanism that explicitly enforces geometric diversity. Building upon this, to specifically solve CMOPs, we develop the Diffusion-based Evolutionary Molecular Optimization (DEMO) framework, utilizing a tri-population architecture with distinct responsibilities to safely navigate disjoint feasible regions. Extensive experiments across single-property targeting, unconstrained MOPs, multi-fragment constrained generation, and 3D protein-ligand docking demonstrate that DEMO comprehensively outperforms train-free guidance methods and EA baselines. Without any model retraining, DEMO successfully discovers highly diverse, chemically valid Pareto frontiers, establishing a robust paradigm for complex 3D molecular optimization.

Zijian Gao, YiYing Li, Kele Xu et al.

The sparsity of extrinsic rewards poses a serious challenge for reinforcement learning (RL). Currently, many efforts have been made on curiosity which can provide a representative intrinsic reward for effective exploration. However, the challenge is still far from being solved. In this paper, we present a novel curiosity for RL, named DyMeCu, which stands for Dynamic Memory-based Curiosity. Inspired by human curiosity and information theory, DyMeCu consists of a dynamic memory and dual online learners. The curiosity arouses if memorized information can not deal with the current state, and the information gap between dual learners can be formulated as the intrinsic reward for agents, and then such state information can be consolidated into the dynamic memory. Compared with previous curiosity methods, DyMeCu can better mimic human curiosity with dynamic memory, and the memory module can be dynamically grown based on a bootstrap paradigm with dual learners. On multiple benchmarks including DeepMind Control Suite and Atari Suite, large-scale empirical experiments are conducted and the results demonstrate that DyMeCu outperforms competitive curiosity-based methods with or without extrinsic rewards. We will release the code to enhance reproducibility.

Jianfei Liu, Rui Li, Zhilin Yang et al.

Existing serverless workflow orchestration systems are predominantly designed for a single-cloud FaaS system, leading to vendor lock-in. This restricts performance optimization, cost reduction, and availability of applications. However, orchestrating serverless workflows on Jointcloud FaaS systems faces two main challenges: (1) additional overhead caused by centralized cross-cloud orchestration; and (2) a lack of reliable failover and fault-tolerant mechanisms for cross-cloud serverless workflows. To address these challenges, we propose Joint$λ$, a distributed runtime system designed to orchestrate serverless workflows on multiple FaaS systems without relying on a centralized orchestrator. Joint$λ$ introduces a compatibility layer, Backend-Shim, leveraging inter-cloud heterogeneity to optimize makespan and reduce costs with on-demand billing. By using function-side orchestration instead of centralized nodes, it enables independent function invocations and data transfers, reducing cross-cloud communication overhead. For high availability, it ensures exactly-once execution via datastores and failover mechanisms for serverless workflows on Jointcloud FaaS systems. We validate Joint$λ$ on two heterogeneous FaaS systems, AWS and Aliyun, with four workflows. Compared to the most advanced commercial orchestration services for single-cloud serverless workflows, Joint$λ$ reduces makespan by up to 3.3$\times$ while saving up to 65% in cost. Joint$λ$ is also up to 4.0$\times$ faster than state-of-the-art orchestrators for cross-cloud serverless workflows, while achieving competitive cost in representative scenarios and providing strong execution guarantees.

Rui Li, Zhaoning Zhang, Libo Zhang et al.

Speculative decoding (SD) accelerates LLM inference by verifying draft tokens in parallel. However, this method presents a critical trade-off: it improves throughput in low-load, memory-bound systems but degrades performance in high-load, compute-bound environments due to verification overhead. Existing speculative decoding methods use fixed lengths and cannot adapt to workload changes or decide when to stop speculation. The cost of restarting speculative inference also remains unquantified. Under high load, the benefit of speculation diminishes, while retaining the draft model reduces KV-cache capacity, limiting batch size and degrading throughput. To overcome this, we propose Nightjar, a resource-aware adaptive speculative framework. It first adjusts to the request load by dynamically selecting the optimal speculative length for different batch sizes. Crucially, Nightjar proactively disables speculative decoding when the MAB planner determines that speculation is no longer beneficial, and during the disabled phase, offloads the draft model to the CPU only under GPU memory pressure. This reclaims memory for the KV cache, thereby facilitating larger batch sizes and maximizing overall system throughput. Experiments show that Nightjar achieves average 27.29% higher throughput and up to 20.18% lower latency compared to standard speculative decoding under dynamic request arrival rates in real-time LLM serving scenarios.

Xunhui Zhang, Tao Wang, Yue Yu et al.

While many forms of financial support are currently available, there are still many complaints about inadequate financing from software maintainers. In May 2019, GitHub, the world's most active social coding platform, launched the Sponsor mechanism as a step toward more deeply integrating open source development and financial support. This paper collects data on 8,028 maintainers, 13,555 sponsors, and 22,515 sponsorships and conducts a comprehensive analysis. We explore the relationship between the Sponsor mechanism and developers along four dimensions using a combination of qualitative and quantitative analysis, examining why developers participate, how the mechanism affects developer activity, who obtains more sponsorships, and what mechanism flaws developers have encountered in the process of using it. We find a long-tail effect in the act of sponsorship, with most maintainers' expectations remaining unmet, and sponsorship has only a short-term, slightly positive impact on development activity but is not sustainable. While sponsors participate in this mechanism mainly as a means of thanking the developers of OSS that they use, in practice, the social status of developers is the primary influence on the number of sponsorships. We find that both the Sponsor mechanism and open source donations have certain shortcomings and need further improvements to attract more participants.

Chaojie Zhao, Peng Zhang, Jian Zhu et al.

A challenge in speech production research is to predict future tongue movements based on a short period of past tongue movements. This study tackles speaker-dependent tongue motion prediction problem in unlabeled ultrasound videos with convolutional long short-term memory (ConvLSTM) networks. The model has been tested on two different ultrasound corpora. ConvLSTM outperforms 3-dimensional convolutional neural network (3DCNN) in predicting the 9\textsuperscript{th} frames based on 8 preceding frames, and also demonstrates good capacity to predict only the tongue contours in future frames. Further tests reveal that ConvLSTM can also learn to predict tongue movements in more distant frames beyond the immediately following frames. Our codes are available at: https://github.com/shuiliwanwu/ConvLstm-ultrasound-videos.

Mingyang Geng, Kele Xu, Bo Ding et al.

Previous attempts for data augmentation are designed manually, and the augmentation policies are dataset-specific. Recently, an automatic data augmentation approach, named AutoAugment, is proposed using reinforcement learning. AutoAugment searches for the augmentation polices in the discrete search space, which may lead to a sub-optimal solution. In this paper, we employ the Augmented Random Search method (ARS) to improve the performance of AutoAugment. Our key contribution is to change the discrete search space to continuous space, which will improve the searching performance and maintain the diversities between sub-policies. With the proposed method, state-of-the-art accuracies are achieved on CIFAR-10, CIFAR-100, and ImageNet (without additional data). Our code is available at https://github.com/gmy2013/ARS-Aug.

Kele Xu, Boqing Zhu, Qiuqiang Kong et al.

Audio tagging aims to infer descriptive labels from audio clips. Audio tagging is challenging due to the limited size of data and noisy labels. In this paper, we describe our solution for the DCASE 2018 Task 2 general audio tagging challenge. The contributions of our solution include: We investigated a variety of convolutional neural network architectures to solve the audio tagging task. Statistical features are applied to capture statistical patterns of audio features to improve the classification performance. Ensemble learning is applied to ensemble the outputs from the deep classifiers to utilize complementary information. a sample re-weight strategy is employed for ensemble training to address the noisy label problem. Our system achieves a mean average precision (mAP@3) of 0.958, outperforming the baseline system of 0.704. Our system ranked the 1st and 4th out of 558 submissions in the public and private leaderboard of DCASE 2018 Task 2 challenge. Our codes are available at https://github.com/Cocoxili/DCASE2018Task2/.

Yuanzhao Zhai, Han Zhang, Yu Lei et al.

Reinforcement learning from human feedback (RLHF) emerges as a promising paradigm for aligning large language models (LLMs). However, a notable challenge in RLHF is overoptimization, where beyond a certain threshold, the pursuit of higher rewards leads to a decline in human preferences. In this paper, we observe the weakness of KL regularization which is commonly employed in existing RLHF methods to address overoptimization. To mitigate this limitation, we scrutinize the RLHF objective in the offline dataset and propose uncertainty-penalized RLHF (UP-RLHF), which incorporates uncertainty regularization during RL-finetuning. To enhance the uncertainty quantification abilities for reward models, we first propose a diverse low-rank adaptation (LoRA) ensemble by maximizing the nuclear norm of LoRA matrix concatenations. Then we optimize policy models utilizing penalized rewards, determined by both rewards and uncertainties provided by the diverse reward LoRA ensembles. Our experimental results, based on two real human preference datasets, showcase the effectiveness of diverse reward LoRA ensembles in quantifying reward uncertainty. Additionally, uncertainty regularization in UP-RLHF proves to be pivotal in mitigating overoptimization, thereby contributing to the overall performance.

Yuanzhao Zhai, Yiying Li, Zijian Gao et al.

Model-based offline reinforcement learning (RL) has made remarkable progress, offering a promising avenue for improving generalization with synthetic model rollouts. Existing works primarily focus on incorporating pessimism for policy optimization, usually via constructing a Pessimistic Markov Decision Process (P-MDP). However, the P-MDP discourages the policies from learning in out-of-distribution (OOD) regions beyond the support of offline datasets, which can under-utilize the generalization ability of dynamics models. In contrast, we propose constructing an Optimistic MDP (O-MDP). We initially observed the potential benefits of optimism brought by encouraging more OOD rollouts. Motivated by this observation, we present ORPO, a simple yet effective model-based offline RL framework. ORPO generates Optimistic model Rollouts for Pessimistic offline policy Optimization. Specifically, we train an optimistic rollout policy in the O-MDP to sample more OOD model rollouts. Then we relabel the sampled state-action pairs with penalized rewards and optimize the output policy in the P-MDP. Theoretically, we demonstrate that the performance of policies trained with ORPO can be lower-bounded in linear MDPs. Experimental results show that our framework significantly outperforms P-MDP baselines by a margin of 30%, achieving state-of-the-art performance on the widely-used benchmark. Moreover, ORPO exhibits notable advantages in problems that require generalization.

Ruiqing Sun, Dawei Feng, Sheng Qi et al.

Existing evolutionary algorithms for Constrained Multi-objective Optimization Problems (CMOPs) typically treat all constraints uniformly, overlooking their distinct geometric relationships with the true Constrained Pareto Front (CPF). In reality, constraints play different roles: some directly shape the final CPF, some create infeasible obstacles, while others are irrelevant. To exploit this insight, we propose a novel algorithm named RCCMO, which sequentially performs unconstrained exploration, single-constraint exploitation, and full-constraint refinement. The core innovation of RCCMO lies in a constraint prioritization method derived from these geometric insights, seamlessly coupled with a unique dual-directional search mechanism. Specifically, RCCMO first prioritizes constraints that constitute the final CPF, approaching them from the evolutionary direction (optimizing objectives) to locate the CPF directly shaped by single-constraint boundaries. Subsequently, for constraints that merely hinder the population's progress, RCCMO searches from the anti-evolutionary direction (targeting the infeasible boundaries where hindering constraints intersect with the CPF) to effectively discover how these constraints obstruct and form the final CPF. Meanwhile, irrelevant constraints are intentionally bypassed. Furthermore, a series of specialized mechanisms are proposed to accelerate the algorithm's execution, reduce heuristic misjudgments, and dynamically adjust search directions in real time. Extensive experiments on 5 benchmark test suites and 29 real-world CMOPs demonstrate that RCCMO significantly outperforms seven state-of-the-art algorithms.

Qiang Wang, Dawei Feng, Xu Zhang et al.

Instruction tuning has emerged as a paramount method for tailoring the behaviors of LLMs. Recent work has unveiled the potential for LLMs to achieve high performance through fine-tuning with a limited quantity of high-quality instruction data. Building upon this approach, we further explore the impact of prompt's robustness on the selection of high-quality instruction data. This paper proposes a pioneering framework of high-quality online instruction data mining for instruction tuning, focusing on the impact of prompt's robustness on the data mining process. Our notable innovation, is to generate the adversarial instruction data by conducting the attack for the prompt of online instruction data. Then, we introduce an Adversarial Instruction-Following Difficulty metric to measure how much help the adversarial instruction data can provide to the generation of the corresponding response. Apart from it, we propose a novel Adversarial Instruction Output Embedding Consistency approach to select high-quality online instruction data. We conduct extensive experiments on two benchmark datasets to assess the performance. The experimental results serve to underscore the effectiveness of our proposed two methods. Moreover, the results underscore the critical practical significance of considering prompt's robustness.

Fei Gao, Ming Hu, Zhiyu Xie et al.

With advancements in AI infrastructure and Trusted Execution Environment (TEE) technology, Federated Learning as a Service (FLaaS) through JointCloud Computing (JCC) is promising to break through the resource constraints caused by heterogeneous edge devices in the traditional Federated Learning (FL) paradigm. Specifically, with the protection from TEE, data owners can achieve efficient model training with high-performance AI services in the cloud. By providing additional FL services, cloud service providers can achieve collaborative learning among data owners. However, FLaaS still faces three challenges, i.e., i) low training performance caused by heterogeneous data among data owners, ii) high communication overhead among different clouds (i.e., data centers), and iii) lack of efficient resource scheduling strategies to balance training time and cost. To address these challenges, this paper presents a novel asynchronous FL approach named NebulaFL for collaborative model training among multiple clouds. To address data heterogeneity issues, NebulaFL adopts a version control-based asynchronous FL training scheme in each data center to balance training time among data owners. To reduce communication overhead, NebulaFL adopts a decentralized model rotation mechanism to achieve effective knowledge sharing among data centers. To balance training time and cost, NebulaFL integrates a reward-guided strategy for data owners selection and resource scheduling. The experimental results demonstrate that, compared to the state-of-the-art FL methods, NebulaFL can achieve up to 5.71\% accuracy improvement. In addition, NebulaFL can reduce up to 50% communication overhead and 61.94% costs under a target accuracy.

Yuanzhao Zhai, Zhuo Zhang, Kele Xu et al.

Aligning with human preference datasets has been critical to the success of large language models (LLMs). Reinforcement learning from human feedback (RLHF) employs a costly reward model to provide feedback for on-policy sampling responses. Recently, offline methods that directly fit responses with binary preferences in the dataset have emerged as alternatives. However, existing methods do not explicitly model preference strength information, which is crucial for distinguishing different response pairs. To overcome this limitation, we propose Online Self-Preferring (OSP) language models to learn from self-generated response pairs and self-judged preference strengths. For each prompt and corresponding self-generated responses, we introduce a ranked pairing method to construct multiple response pairs with preference strength information. We then propose the soft-preference cross-entropy loss to leverage such information. Empirically, we demonstrate that leveraging preference strength is crucial for avoiding overfitting and enhancing alignment performance. OSP achieves state-of-the-art alignment performance across various metrics in two widely used human preference datasets. OSP is parameter-efficient and more robust than the dominant online method, RLHF when limited offline data are available and generalizing to out-of-domain tasks. Moreover, OSP language models established by LLMs with proficiency in self-preferring can efficiently self-improve without external supervision.

Xunhui Zhang, Tao Wang, Yue Yu et al.

The application of code clone technology accelerates code search, improves code reuse efficiency, and assists in software quality assessment and code vulnerability detection. However, the application of code clones also introduces software quality issues and increases the cost of software maintenance. As an important research field in software engineering, code clone has been extensively explored and studied by researchers, and related studies on various sub-research fields have emerged, including code clone detection, code clone evolution, code clone analysis, etc. However, there lacks a comprehensive exploration of the entire field of code clone, as well as an analysis of the trend of each sub-research field. This paper collects related work of code clones in the past ten years. In summary, the contributions of this paper mainly include: (1) summarize and classify the sub-research fields of code clone, and explore the relative popularity and relation of these sub-research fields; (2) analyze the overall research trend of code clone and each sub-research field; (3) compare and analyze the difference between academy and industry regarding code clone research; (4) construct a network of researchers, and excavate the major contributors in code clone research field; (5) The list of popular conferences and journals was statistically analyzed. The popular research directions in the future include clone visualization, clone management, etc. For the clone detection technique, researchers can optimize the scalability and execution efficiency of the method, targeting particular clone detection tasks and contextual environments, or apply the technology to other related research fields continuously.

Da Li, Sen Yang, Kele Xu et al.

Semantic networks, such as the knowledge graph, can represent the knowledge leveraging the graph structure. Although the knowledge graph shows promising values in natural language processing, it suffers from incompleteness. This paper focuses on knowledge graph completion by predicting linkage between entities, which is a fundamental yet critical task. Semantic matching is a potential solution as it can deal with unseen entities, which the translational distance based methods struggle with. However, to achieve competitive performance as translational distance based methods, semantic matching based methods require large-scale datasets for the training purpose, which are typically unavailable in practical settings. Therefore, we employ the language model and introduce a novel knowledge graph architecture named LP-BERT, which contains two main stages: multi-task pre-training and knowledge graph fine-tuning. In the pre-training phase, three tasks are taken to drive the model to learn the relationship from triples by predicting either entities or relations. While in the fine-tuning phase, inspired by contrastive learning, we design a triple-style negative sampling in a batch, which greatly increases the proportion of negative sampling while keeping the training time almost unchanged. Furthermore, we propose a new data augmentation method utilizing the inverse relationship of triples to improve the performance and robustness of the model. To demonstrate the effectiveness of our method, we conduct extensive experiments on three widely-used datasets, WN18RR, FB15k-237, and UMLS. The experimental results demonstrate the superiority of our methods, and our approach achieves state-of-the-art results on WN18RR and FB15k-237 datasets. Significantly, Hits@10 indicator is improved by 5% from previous state-of-the-art result on the WN18RR dataset while reaching 100% on the UMLS dataset.

Xunhui Zhang, Yue Yu, Tao Wang et al.

Pull request latency evaluation is an essential application of effort evaluation in the pull-based development scenario. It can help the reviewers sort the pull request queue, remind developers about the review processing time, speed up the review process and accelerate software development. There is a lack of work that systematically organizes the factors that affect pull request latency. Also, there is no related work discussing the differences and variations in characteristics in different scenarios and contexts. In this paper, we collected relevant factors through a literature review approach. Then we assessed their relative importance in five scenarios and six different contexts using the mixed-effects linear regression model. We find that the relative importance of factors differs in different scenarios, e.g., the first response time of the reviewer is most important when there exist comments. Meanwhile, the number of commits in a pull request has a more significant impact on pull request latency when closing than submitting due to changes in contributions brought about by the review process.

Zijian Gao, Kele Xu, Bo Ding et al.

Recently, deep reinforcement learning (RL) algorithms have made great progress in multi-agent domain. However, due to characteristics of RL, training for complex tasks would be resource-intensive and time-consuming. To meet this challenge, mutual learning strategy between homogeneous agents is essential, which is under-explored in previous studies, because most existing methods do not consider to use the knowledge of agent models. In this paper, we present an adaptation method of the majority of multi-agent reinforcement learning (MARL) algorithms called KnowSR which takes advantage of the differences in learning between agents. We employ the idea of knowledge distillation (KD) to share knowledge among agents to shorten the training phase. To empirically demonstrate the robustness and effectiveness of KnowSR, we performed extensive experiments on state-of-the-art MARL algorithms in collaborative and competitive scenarios. The results demonstrate that KnowSR outperforms recently reported methodologies, emphasizing the importance of the proposed knowledge sharing for MARL.

Zijian Gao, Kele Xu, Bo Ding et al.

Recently, deep Reinforcement Learning (RL) algorithms have achieved dramatically progress in the multi-agent area. However, training the increasingly complex tasks would be time-consuming and resources-exhausting. To alleviate this problem, efficient leveraging the historical experience is essential, which is under-explored in previous studies as most of the exiting methods may fail to achieve this goal in a continuously variational system due to their complicated design and environmental dynamics. In this paper, we propose a method, named "KnowRU" for knowledge reusing which can be easily deployed in the majority of the multi-agent reinforcement learning algorithms without complicated hand-coded design. We employ the knowledge distillation paradigm to transfer the knowledge among agents with the goal to accelerate the training phase for new tasks, while improving the asymptotic performance of agents. To empirically demonstrate the robustness and effectiveness of KnowRU, we perform extensive experiments on state-of-the-art multi-agent reinforcement learning (MARL) algorithms on collaborative and competitive scenarios. The results show that KnowRU can outperform the recently reported methods, which emphasizes the importance of the proposed knowledge reusing for MARL.

Yiying Li, Wei Zhou, Huaimin Wang et al.

Federated learning (FL) enables distributed participants to collectively learn a strong global model without sacrificing their individual data privacy. Mainstream FL approaches require each participant to share a common network architecture and further assume that data are are sampled IID across participants. However, in real-world deployments participants may require heterogeneous network architectures; and the data distribution is almost certainly non-uniform across participants. To address these issues we introduce FedH2L, which is agnostic to both the model architecture and robust to different data distributions across participants. In contrast to approaches sharing parameters or gradients, FedH2L relies on mutual distillation, exchanging only posteriors on a shared seed set between participants in a decentralized manner. This makes it extremely bandwidth efficient, model agnostic, and crucially produces models capable of performing well on the whole data distribution when learning from heterogeneous silos.

Boqing Zhu, Kele Xu, Qiuqiang Kong et al.

High quality labeled datasets have allowed deep learning to achieve impressive results on many sound analysis tasks. Yet, it is labor-intensive to accurately annotate large amount of audio data, and the dataset may contain noisy labels in the practical settings. Meanwhile, the deep neural networks are susceptive to those incorrect labeled data because of their outstanding memorization ability. In this paper, we present a novel framework, named CrossFilter, to combat the noisy labels problem for audio tagging. Multiple representations (such as, Logmel and MFCC) are used as the input of our framework for providing more complementary information of the audio. Then, though the cooperation and interaction of two neural networks, we divide the dataset into curated and noisy subsets by incrementally pick out the possibly correctly labeled data from the noisy data. Moreover, our approach leverages the multi-task learning on curated and noisy subsets with different loss function to fully utilize the entire dataset. The noisy-robust loss function is employed to alleviate the adverse effects of incorrect labels. On both the audio tagging datasets FSDKaggle2018 and FSDKaggle2019, empirical results demonstrate the performance improvement compared with other competing approaches. On FSDKaggle2018 dataset, our method achieves state-of-the-art performance and even surpasses the ensemble models.

Wei Zhou, Yiying Li, Yongxin Yang et al.

Off-Policy Actor-Critic (Off-PAC) methods have proven successful in a variety of continuous control tasks. Normally, the critic's action-value function is updated using temporal-difference, and the critic in turn provides a loss for the actor that trains it to take actions with higher expected return. In this paper, we introduce a novel and flexible meta-critic that observes the learning process and meta-learns an additional loss for the actor that accelerates and improves actor-critic learning. Compared to the vanilla critic, the meta-critic network is explicitly trained to accelerate the learning process; and compared to existing meta-learning algorithms, meta-critic is rapidly learned online for a single task, rather than slowly over a family of tasks. Crucially, our meta-critic framework is designed for off-policy based learners, which currently provide state-of-the-art reinforcement learning sample efficiency. We demonstrate that online meta-critic learning leads to improvements in avariety of continuous control environments when combined with contemporary Off-PAC methods DDPG, TD3 and the state-of-the-art SAC.

Liang Gao, Kele Xu, Huaimin Wang et al.

As an important component of multimedia analysis tasks, audio classification aims to discriminate between different audio signal types and has received intensive attention due to its wide applications. Generally speaking, the raw signal can be transformed into various representations (such as Short Time Fourier Transform and Mel Frequency Cepstral Coefficients), and information implied in different representations can be complementary. Ensembling the models trained on different representations can greatly boost the classification performance, however, making inference using a large number of models is cumbersome and computationally expensive. In this paper, we propose a novel end-to-end collaborative learning framework for the audio classification task. The framework takes multiple representations as the input to train the models in parallel. The complementary information provided by different representations is shared by knowledge distillation. Consequently, the performance of each model can be significantly promoted without increasing the computational overhead in the inference stage. Extensive experimental results demonstrate that the proposed approach can improve the classification performance and achieve state-of-the-art results on both acoustic scene classification tasks and general audio tagging tasks.

Mingyang Geng, Kele Xu, Yiying Li et al.

The aim of multi-agent reinforcement learning systems is to provide interacting agents with the ability to collaboratively learn and adapt to the behavior of other agents. In many real-world applications, the agents can only acquire a partial view of the world. However, in realistic settings, one or more agents that show arbitrarily faulty or malicious behavior may suffice to let the current coordination mechanisms fail. In this paper, we study a practical scenario considering the security issues in the presence of agents with arbitrarily faulty or malicious behavior. Under these circumstances, learning an optimal policy becomes particularly challenging, even in the unrealistic case that an agent's policy can be made conditional upon all other agents' observations. To overcome these difficulties, we present an Attention-based Fault-Tolerant (FT-Attn) algorithm which selects correct and relevant information for each agent at every time-step. The multi-head attention mechanism enables the agents to learn effective communication policies through experience concurrently to the action policies. Empirical results have shown that FT-Attn beats previous state-of-the-art methods in some complex environments and can adapt to various kinds of noisy environments without tuning the complexity of the algorithm. Furthermore, FT-Attn can effectively deal with the complex situation where an agent needs to reach multiple agents' correct observation at the same time.

Mingyang Geng, Suning Shang, Bo Ding et al.

The RGB-D camera maintains a limited range for working and is hard to accurately measure the depth information in a far distance. Besides, the RGB-D camera will easily be influenced by strong lighting and other external factors, which will lead to a poor accuracy on the acquired environmental depth information. Recently, deep learning technologies have achieved great success in the visual SLAM area, which can directly learn high-level features from the visual inputs and improve the estimation accuracy of the depth information. Therefore, deep learning technologies maintain the potential to extend the source of the depth information and improve the performance of the SLAM system. However, the existing deep learning-based methods are mainly supervised and require a large amount of ground-truth depth data, which is hard to acquire because of the realistic constraints. In this paper, we first present an unsupervised learning framework, which not only uses image reconstruction for supervising but also exploits the pose estimation method to enhance the supervised signal and add training constraints for the task of monocular depth and camera motion estimation. Furthermore, we successfully exploit our unsupervised learning framework to assist the traditional ORB-SLAM system when the initialization module of ORB-SLAM method could not match enough features. Qualitative and quantitative experiments have shown that our unsupervised learning framework performs the depth estimation task comparable to the supervised methods and outperforms the previous state-of-the-art approach by $13.5\%$ on KITTI dataset. Besides, our unsupervised learning framework could significantly accelerate the initialization process of ORB-SLAM system and effectively improve the accuracy on environmental mapping in strong lighting and weak texture scenes.

Kele Xu, Haibo Mi, Dawei Feng et al.

Valuable training data is often owned by independent organizations and located in multiple data centers. Most deep learning approaches require to centralize the multi-datacenter data for performance purpose. In practice, however, it is often infeasible to transfer all data to a centralized data center due to not only bandwidth limitation but also the constraints of privacy regulations. Model averaging is a conventional choice for data parallelized training, but its ineffectiveness is claimed by previous studies as deep neural networks are often non-convex. In this paper, we argue that model averaging can be effective in the decentralized environment by using two strategies, namely, the cyclical learning rate and the increased number of epochs for local model training. With the two strategies, we show that model averaging can provide competitive performance in the decentralized mode compared to the data-centralized one. In a practical environment with multiple data centers, we conduct extensive experiments using state-of-the-art deep network architectures on different types of data. Results demonstrate the effectiveness and robustness of the proposed method.

Shengyun Wei, Kele Xu, Dezhi Wang et al.

Audio tagging has attracted increasing attention since last decade and has various potential applications in many fields. The objective of audio tagging is to predict the labels of an audio clip. Recently deep learning methods have been applied to audio tagging and have achieved state-of-the-art performance, which provides a poor generalization ability on new data. However due to the limited size of audio tagging data such as DCASE data, the trained models tend to result in overfitting of the network. Previous data augmentation methods such as pitch shifting, time stretching and adding background noise do not show much improvement in audio tagging. In this paper, we explore the sample mixed data augmentation for the domestic audio tagging task, including mixup, SamplePairing and extrapolation. We apply a convolutional recurrent neural network (CRNN) with attention module with log-scaled mel spectrum as a baseline system. In our experiments, we achieve an state-of-the-art of equal error rate (EER) of 0.10 on DCASE 2016 task4 dataset with mixup approach, outperforming the baseline system without data augmentation.

Ben Hu, Huaimin Wang, Pengfei Zhang et al.

Many robotic tasks require heavy computation, which can easily exceed the robot's onboard computer capability. A promising solution to address this challenge is outsourcing the computation to the cloud. However, exploiting the potential of cloud resources in robotic software is difficult, because it involves complex code modification and extensive (re)configuration procedures. Moreover, quality of service (QoS) such as timeliness, which is critical to robot's behavior, have to be considered. In this paper, we propose a transparent and QoS-aware software framework called Cloudroid for cloud robotic applications. This framework supports direct deployment of existing robotic software packages to the cloud, transparently transforming them into Internet-accessible cloud services. And with the automatically generated service stubs, robotic applications can outsource their computation to the cloud without any code modification. Furthermore, the robot and the cloud can cooperate to maintain the specific QoS property such as request response time, even in a highly dynamic and resource-competitive environment. We evaluated Cloudroid based on a group of typical robotic scenarios and a set of software packages widely adopted in real-world robot practices. Results show that robot's capability can be enhanced significantly without code modification and specific QoS objectives can be guaranteed. In certain tasks, the "cloud + robot" setup shows improved performance in orders of magnitude compared with the robot native setup.

Yue Yu, Bogdan Vasilescu, Huaimin Wang et al.

The constant demand for new features and bug fixes are forcing software projects to shorten cycles and deliver updates ever faster, while sustaining software quality. The availability of inexpensive, virtualized, cloud-computing has helped shorten schedules, by enabling continuous integration (CI) on demand. Platforms like GitHub support CI in-the-cloud. In projects using CI, a user submitting a pull request triggers a CI step. Besides speeding up build and test, this fortuitously creates voluminous archives of build and test successes and failures. CI is a relatively new phenomenon, and these archives allow a detailed study of CI. How many problems are exposed? Where do they occur? What factors affect CI failures? Does the "initial quality" as ascertained by CI predict how many bugs will later appear ("eventual quality") in the code? In this paper, we undertake a large-scale, fine resolution study of these records, to better understand CI processes, the nature, and predictors of CI failures, and the relationship of CI failures to the eventual quality of the code. We find that: a) CI failures appear to be concentrated in a few files, just like normal bugs; b) CI failures are not very highly correlated with eventual failures; c) The use of CI in a pull request doesn't necessarily mean the code in that request is of good quality.