Bo Yuan

Huy Phan, Cong Shi, Yi Xie et al.

Recently backdoor attack has become an emerging threat to the security of deep neural network (DNN) models. To date, most of the existing studies focus on backdoor attack against the uncompressed model; while the vulnerability of compressed DNNs, which are widely used in the practical applications, is little exploited yet. In this paper, we propose to study and develop Robust and Imperceptible Backdoor Attack against Compact DNN models (RIBAC). By performing systematic analysis and exploration on the important design knobs, we propose a framework that can learn the proper trigger patterns, model parameters and pruning masks in an efficient way. Thereby achieving high trigger stealthiness, high attack success rate and high model efficiency simultaneously. Extensive evaluations across different datasets, including the test against the state-of-the-art defense mechanisms, demonstrate the high robustness, stealthiness and model efficiency of RIBAC. Code is available at https://github.com/huyvnphan/ECCV2022-RIBAC

Linrui Zhang, Qin Zhang, Li Shen et al.

Safe reinforcement learning (RL) has achieved significant success on risk-sensitive tasks and shown promise in autonomous driving (AD) as well. Considering the distinctiveness of this community, efficient and reproducible baselines are still lacking for safe AD. In this paper, we release SafeRL-Kit to benchmark safe RL methods for AD-oriented tasks. Concretely, SafeRL-Kit contains several latest algorithms specific to zero-constraint-violation tasks, including Safety Layer, Recovery RL, off-policy Lagrangian method, and Feasible Actor-Critic. In addition to existing approaches, we propose a novel first-order method named Exact Penalty Optimization (EPO) and sufficiently demonstrate its capability in safe AD. All algorithms in SafeRL-Kit are implemented (i) under the off-policy setting, which improves sample efficiency and can better leverage past logs; (ii) with a unified learning framework, providing off-the-shelf interfaces for researchers to incorporate their domain-specific knowledge into fundamental safe RL methods. Conclusively, we conduct a comparative evaluation of the above algorithms in SafeRL-Kit and shed light on their efficacy for safe autonomous driving. The source code is available at \href{ https://github.com/zlr20/saferl_kit}{this https URL}.

Zongyi Xu, Bo Yuan, Shanshan Zhao et al.

Impressive performance on point cloud semantic segmentation has been achieved by fully-supervised methods with large amounts of labelled data. As it is labour-intensive to acquire large-scale point cloud data with point-wise labels, many attempts have been made to explore learning 3D point cloud segmentation with limited annotations. Active learning is one of the effective strategies to achieve this purpose but is still under-explored. The most recent methods of this kind measure the uncertainty of each pre-divided region for manual labelling but they suffer from redundant information and require additional efforts for region division. This paper aims at addressing this issue by developing a hierarchical point-based active learning strategy. Specifically, we measure the uncertainty for each point by a hierarchical minimum margin uncertainty module which considers the contextual information at multiple levels. Then, a feature-distance suppression strategy is designed to select important and representative points for manual labelling. Besides, to better exploit the unlabelled data, we build a semi-supervised segmentation framework based on our active strategy. Extensive experiments on the S3DIS and ScanNetV2 datasets demonstrate that the proposed framework achieves 96.5% and 100% performance of fully-supervised baseline with only 0.07% and 0.1% training data, respectively, outperforming the state-of-the-art weakly-supervised and active learning methods. The code will be available at https://github.com/SmiletoE/HPAL.

Bo Yuan, Danpei Zhao

Continual learning, also known as incremental learning or life-long learning, stands at the forefront of deep learning and AI systems. It breaks through the obstacle of one-way training on close sets and enables continuous adaptive learning on open-set conditions. In the recent decade, continual learning has been explored and applied in multiple fields especially in computer vision covering classification, detection and segmentation tasks. Continual semantic segmentation (CSS), of which the dense prediction peculiarity makes it a challenging, intricate and burgeoning task. In this paper, we present a review of CSS, committing to building a comprehensive survey on problem formulations, primary challenges, universal datasets, neoteric theories and multifarious applications. Concretely, we begin by elucidating the problem definitions and primary challenges. Based on an in-depth investigation of relevant approaches, we sort out and categorize current CSS models into two main branches including data-replay and data-free sets. In each branch, the corresponding approaches are similarity-based clustered and thoroughly analyzed, following qualitative comparison and quantitative reproductions on relevant datasets. Besides, we also introduce four CSS specialities with diverse application scenarios and development tendencies. Furthermore, we develop a benchmark for CSS encompassing representative references, evaluation results and reproductions, which is available at~\url{https://github.com/YBIO/SurveyCSS}. We hope this survey can serve as a reference-worthy and stimulating contribution to the advancement of the life-long learning field, while also providing valuable perspectives for related fields.

Shengyuan Hou, Jushi Kai, Haotian Xue et al. · gatech, meta-ai

Recent works have revealed that Transformers are implicitly learning the syntactic information in its lower layers from data, albeit is highly dependent on the quality and scale of the training data. However, learning syntactic information from data is not necessary if we can leverage an external syntactic parser, which provides better parsing quality with well-defined syntactic structures. This could potentially improve Transformer's performance and sample efficiency. In this work, we propose a syntax-guided localized self-attention for Transformer that allows directly incorporating grammar structures from an external constituency parser. It prohibits the attention mechanism to overweight the grammatically distant tokens over close ones. Experimental results show that our model could consistently improve translation performance on a variety of machine translation datasets, ranging from small to large dataset sizes, and with different source languages.

Ning Shi, Bin Tang, Bo Yuan et al. · meta-ai, mila

Text editing, such as grammatical error correction, arises naturally from imperfect textual data. Recent works frame text editing as a multi-round sequence tagging task, where operations -- such as insertion and substitution -- are represented as a sequence of tags. While achieving good results, this encoding is limited in flexibility as all actions are bound to token-level tags. In this work, we reformulate text editing as an imitation game using behavioral cloning. Specifically, we convert conventional sequence-to-sequence data into state-to-action demonstrations, where the action space can be as flexible as needed. Instead of generating the actions one at a time, we introduce a dual decoders structure to parallel the decoding while retaining the dependencies between action tokens, coupled with trajectory augmentation to alleviate the distribution shift that imitation learning often suffers. In experiments on a suite of Arithmetic Equation benchmarks, our model consistently outperforms the autoregressive baselines in terms of performance, efficiency, and robustness. We hope our findings will shed light on future studies in reinforcement learning applying sequence-level action generation to natural language processing.

Linrui Zhang, Li Shen, Long Yang et al.

Safe reinforcement learning aims to learn the optimal policy while satisfying safety constraints, which is essential in real-world applications. However, current algorithms still struggle for efficient policy updates with hard constraint satisfaction. In this paper, we propose Penalized Proximal Policy Optimization (P3O), which solves the cumbersome constrained policy iteration via a single minimization of an equivalent unconstrained problem. Specifically, P3O utilizes a simple-yet-effective penalty function to eliminate cost constraints and removes the trust-region constraint by the clipped surrogate objective. We theoretically prove the exactness of the proposed method with a finite penalty factor and provide a worst-case analysis for approximate error when evaluated on sample trajectories. Moreover, we extend P3O to more challenging multi-constraint and multi-agent scenarios which are less studied in previous work. Extensive experiments show that P3O outperforms state-of-the-art algorithms with respect to both reward improvement and constraint satisfaction on a set of constrained locomotive tasks.

Yifan Shi, Li Shen, Kang Wei et al.

To mitigate the privacy leakages and communication burdens of Federated Learning (FL), decentralized FL (DFL) discards the central server and each client only communicates with its neighbors in a decentralized communication network. However, existing DFL suffers from high inconsistency among local clients, which results in severe distribution shift and inferior performance compared with centralized FL (CFL), especially on heterogeneous data or sparse communication topology. To alleviate this issue, we propose two DFL algorithms named DFedSAM and DFedSAM-MGS to improve the performance of DFL. Specifically, DFedSAM leverages gradient perturbation to generate local flat models via Sharpness Aware Minimization (SAM), which searches for models with uniformly low loss values. DFedSAM-MGS further boosts DFedSAM by adopting Multiple Gossip Steps (MGS) for better model consistency, which accelerates the aggregation of local flat models and better balances communication complexity and generalization. Theoretically, we present improved convergence rates $\small \mathcal{O}\big(\frac{1}{\sqrt{KT}}+\frac{1}{T}+\frac{1}{K^{1/2}T^{3/2}(1-λ)^2}\big)$ and $\small \mathcal{O}\big(\frac{1}{\sqrt{KT}}+\frac{1}{T}+\frac{λ^Q+1}{K^{1/2}T^{3/2}(1-λ^Q)^2}\big)$ in non-convex setting for DFedSAM and DFedSAM-MGS, respectively, where $1-λ$ is the spectral gap of gossip matrix and $Q$ is the number of MGS. Empirically, our methods can achieve competitive performance compared with CFL methods and outperform existing DFL methods.

Qin Zhang, Linrui Zhang, Haoran Xu et al.

Offline safe RL is of great practical relevance for deploying agents in real-world applications. However, acquiring constraint-satisfying policies from the fixed dataset is non-trivial for conventional approaches. Even worse, the learned constraints are stationary and may become invalid when the online safety requirement changes. In this paper, we present a novel offline safe RL approach referred to as SaFormer, which tackles the above issues via conditional sequence modeling. In contrast to existing sequence models, we propose cost-related tokens to restrict the action space and a posterior safety verification to enforce the constraint explicitly. Specifically, SaFormer performs a two-stage auto-regression conditioned by the maximum remaining cost to generate feasible candidates. It then filters out unsafe attempts and executes the optimal action with the highest expected return. Extensive experiments demonstrate the efficacy of SaFormer featuring (1) competitive returns with tightened constraint satisfaction; (2) adaptability to the in-range cost values of the offline data without retraining; (3) generalizability for constraints beyond the current dataset.

Zhecheng Yuan, Zhengrong Xue, Bo Yuan et al.

Learning generalizable policies that can adapt to unseen environments remains challenging in visual Reinforcement Learning (RL). Existing approaches try to acquire a robust representation via diversifying the appearances of in-domain observations for better generalization. Limited by the specific observations of the environment, these methods ignore the possibility of exploring diverse real-world image datasets. In this paper, we investigate how a visual RL agent would benefit from the off-the-shelf visual representations. Surprisingly, we find that the early layers in an ImageNet pre-trained ResNet model could provide rather generalizable representations for visual RL. Hence, we propose Pre-trained Image Encoder for Generalizable visual reinforcement learning (PIE-G), a simple yet effective framework that can generalize to the unseen visual scenarios in a zero-shot manner. Extensive experiments are conducted on DMControl Generalization Benchmark, DMControl Manipulation Tasks, Drawer World, and CARLA to verify the effectiveness of PIE-G. Empirical evidence suggests PIE-G improves sample efficiency and significantly outperforms previous state-of-the-art methods in terms of generalization performance. In particular, PIE-G boasts a 55% generalization performance gain on average in the challenging video background setting. Project Page: https://sites.google.com/view/pie-g/home.

Guozheng Ma, Zhen Wang, Zhecheng Yuan et al.

Visual reinforcement learning (RL), which makes decisions directly from high-dimensional visual inputs, has demonstrated significant potential in various domains. However, deploying visual RL techniques in the real world remains challenging due to their low sample efficiency and large generalization gaps. To tackle these obstacles, data augmentation (DA) has become a widely used technique in visual RL for acquiring sample-efficient and generalizable policies by diversifying the training data. This survey aims to provide a timely and essential review of DA techniques in visual RL in recognition of the thriving development in this field. In particular, we propose a unified framework for analyzing visual RL and understanding the role of DA in it. We then present a principled taxonomy of the existing augmentation techniques used in visual RL and conduct an in-depth discussion on how to better leverage augmented data in different scenarios. Moreover, we report a systematic empirical evaluation of DA-based techniques in visual RL and conclude by highlighting the directions for future research. As the first comprehensive survey of DA in visual RL, this work is expected to offer valuable guidance to this emerging field.

Tiantian Zhang, Zichuan Lin, Yuxing Wang et al.

A key challenge of continual reinforcement learning (CRL) in dynamic environments is to promptly adapt the RL agent's behavior as the environment changes over its lifetime, while minimizing the catastrophic forgetting of the learned information. To address this challenge, in this article, we propose DaCoRL, i.e., dynamics-adaptive continual RL. DaCoRL learns a context-conditioned policy using progressive contextualization, which incrementally clusters a stream of stationary tasks in the dynamic environment into a series of contexts and opts for an expandable multihead neural network to approximate the policy. Specifically, we define a set of tasks with similar dynamics as an environmental context and formalize context inference as a procedure of online Bayesian infinite Gaussian mixture clustering on environment features, resorting to online Bayesian inference to infer the posterior distribution over contexts. Under the assumption of a Chinese restaurant process prior, this technique can accurately classify the current task as a previously seen context or instantiate a new context as needed without relying on any external indicator to signal environmental changes in advance. Furthermore, we employ an expandable multihead neural network whose output layer is synchronously expanded with the newly instantiated context, and a knowledge distillation regularization term for retaining the performance on learned tasks. As a general framework that can be coupled with various deep RL algorithms, DaCoRL features consistent superiority over existing methods in terms of the stability, overall performance and generalization ability, as verified by extensive experiments on several robot navigation and MuJoCo locomotion tasks.

Huy Phan, Miao Yin, Yang Sui et al.

Model compression and model defense for deep neural networks (DNNs) have been extensively and individually studied. Considering the co-importance of model compactness and robustness in practical applications, several prior works have explored to improve the adversarial robustness of the sparse neural networks. However, the structured sparse models obtained by the exiting works suffer severe performance degradation for both benign and robust accuracy, thereby causing a challenging dilemma between robustness and structuredness of the compact DNNs. To address this problem, in this paper, we propose CSTAR, an efficient solution that can simultaneously impose the low-rankness-based Compactness, high STructuredness and high Adversarial Robustness on the target DNN models. By formulating the low-rankness and robustness requirement within the same framework and globally determining the ranks, the compressed DNNs can simultaneously achieve high compression performance and strong adversarial robustness. Evaluations for various DNN models on different datasets demonstrate the effectiveness of CSTAR. Compared with the state-of-the-art robust structured pruning methods, CSTAR shows consistently better performance. For instance, when compressing ResNet-18 on CIFAR-10, CSTAR can achieve up to 20.07% and 11.91% improvement for benign accuracy and robust accuracy, respectively. For compressing ResNet-18 with 16x compression ratio on Imagenet, CSTAR can obtain 8.58% benign accuracy gain and 4.27% robust accuracy gain compared to the existing robust structured pruning method.

Zihan Zhang, Jinfeng Li, Ning Shi et al.

Despite of the superb performance on a wide range of tasks, pre-trained language models (e.g., BERT) have been proved vulnerable to adversarial texts. In this paper, we present RoChBERT, a framework to build more Robust BERT-based models by utilizing a more comprehensive adversarial graph to fuse Chinese phonetic and glyph features into pre-trained representations during fine-tuning. Inspired by curriculum learning, we further propose to augment the training dataset with adversarial texts in combination with intermediate samples. Extensive experiments demonstrate that RoChBERT outperforms previous methods in significant ways: (i) robust -- RoChBERT greatly improves the model robustness without sacrificing accuracy on benign texts. Specifically, the defense lowers the success rates of unlimited and limited attacks by 59.43% and 39.33% respectively, while remaining accuracy of 93.30%; (ii) flexible -- RoChBERT can easily extend to various language models to solve different downstream tasks with excellent performance; and (iii) efficient -- RoChBERT can be directly applied to the fine-tuning stage without pre-training language model from scratch, and the proposed data augmentation method is also low-cost.

Tiantian Zhang, Kevin Zehua Shen, Zichuan Lin et al.

Replaying past experiences has proven to be a highly effective approach for averting catastrophic forgetting in supervised continual learning. However, some crucial factors are still largely ignored, making it vulnerable to serious failure, when used as a solution to forgetting in continual reinforcement learning, even in the context of perfect memory where all data of previous tasks are accessible in the current task. On the one hand, since most reinforcement learning algorithms are not invariant to the reward scale, the previously well-learned tasks (with high rewards) may appear to be more salient to the current learning process than the current task (with small initial rewards). This causes the agent to concentrate on those salient tasks at the expense of generality on the current task. On the other hand, offline learning on replayed tasks while learning a new task may induce a distributional shift between the dataset and the learned policy on old tasks, resulting in forgetting. In this paper, we introduce RECALL, a replay-enhanced method that greatly improves the plasticity of existing replay-based methods on new tasks while effectively avoiding the recurrence of catastrophic forgetting in continual reinforcement learning. RECALL leverages adaptive normalization on approximate targets and policy distillation on old tasks to enhance generality and stability, respectively. Extensive experiments on the Continual World benchmark show that RECALL performs significantly better than purely perfect memory replay, and achieves comparable or better overall performance against state-of-the-art continual learning methods.

Xiao Zang, Jie Chen, Bo Yuan

Graph neural networks (GNNs) are a class of effective deep learning models for node classification tasks; yet their predictive capability may be severely compromised under adversarially designed unnoticeable perturbations to the graph structure and/or node data. Most of the current work on graph adversarial attacks aims at lowering the overall prediction accuracy, but we argue that the resulting abnormal model performance may catch attention easily and invite quick counterattack. Moreover, attacks through modification of existing graph data may be hard to conduct if good security protocols are implemented. In this work, we consider an easier attack harder to be noticed, through adversarially patching the graph with new nodes and edges. The attack is universal: it targets a single node each time and flips its connection to the same set of patch nodes. The attack is unnoticeable: it does not modify the predictions of nodes other than the target. We develop an algorithm, named GUAP, that achieves high attack success rate but meanwhile preserves the prediction accuracy. GUAP is fast to train by employing a sampling strategy. We demonstrate that a 5% sampling in each epoch yields 20x speedup in training, with only a slight degradation in attack performance. Additionally, we show that the adversarial patch trained with the graph convolutional network transfers well to other GNNs, such as the graph attention network.

Cheng Yang, Yang Sui, Jinqi Xiao et al.

The emergence of Mixture of Experts (MoE) LLMs has significantly advanced the development of language models. Compared to traditional LLMs, MoE LLMs outperform traditional LLMs by achieving higher performance with considerably fewer activated parameters. Despite this efficiency, their enormous parameter size still leads to high deployment costs. In this paper, we introduce a two-stage compression method tailored for MoE to reduce the model size and decrease the computational cost. First, in the inter-expert pruning stage, we analyze the importance of each layer and propose the Layer-wise Genetic Search and Block-wise KT-Reception Field with the non-uniform pruning ratio to prune the individual expert. Second, in the intra-expert decomposition stage, we apply the low-rank decomposition to further compress the parameters within the remaining experts. Extensive experiments on Qwen1.5-MoE-A2.7B, DeepSeek-V2-Lite, and Mixtral-8$\times$7B demonstrate that our proposed methods can both reduce the model size and enhance inference efficiency while maintaining performance in various zero-shot tasks. The code will be available at \url{https://github.com/xiaochengsky/MoEI-2.git}

Yangyi Chen, Hongcheng Gao, Ganqu Cui et al.

Textual adversarial attacks can discover models' weaknesses by adding semantic-preserved but misleading perturbations to the inputs. The long-lasting adversarial attack-and-defense arms race in Natural Language Processing (NLP) is algorithm-centric, providing valuable techniques for automatic robustness evaluation. However, the existing practice of robustness evaluation may exhibit issues of incomprehensive evaluation, impractical evaluation protocol, and invalid adversarial samples. In this paper, we aim to set up a unified automatic robustness evaluation framework, shifting towards model-centric evaluation to further exploit the advantages of adversarial attacks. To address the above challenges, we first determine robustness evaluation dimensions based on model capabilities and specify the reasonable algorithm to generate adversarial samples for each dimension. Then we establish the evaluation protocol, including evaluation settings and metrics, under realistic demands. Finally, we use the perturbation degree of adversarial samples to control the sample validity. We implement a toolkit RobTest that realizes our automatic robustness evaluation framework. In our experiments, we conduct a robustness evaluation of RoBERTa models to demonstrate the effectiveness of our evaluation framework, and further show the rationality of each component in the framework. The code will be made public at \url{https://github.com/thunlp/RobTest}.

Tiantian Zhang, Xueqian Wang, Bin Liang et al.

The powerful learning ability of deep neural networks enables reinforcement learning agents to learn competent control policies directly from continuous environments. In theory, to achieve stable performance, neural networks assume i.i.d. inputs, which unfortunately does no hold in the general reinforcement learning paradigm where the training data is temporally correlated and non-stationary. This issue may lead to the phenomenon of "catastrophic interference" and the collapse in performance. In this paper, we present IQ, i.e., interference-aware deep Q-learning, to mitigate catastrophic interference in single-task deep reinforcement learning. Specifically, we resort to online clustering to achieve on-the-fly context division, together with a multi-head network and a knowledge distillation regularization term for preserving the policy of learned contexts. Built upon deep Q networks, IQ consistently boosts the stability and performance when compared to existing methods, verified with extensive experiments on classic control and Atari tasks. The code is publicly available at: https://github.com/Sweety-dm/Interference-aware-Deep-Q-learning.

Yang Sui, Huy Phan, Jinqi Xiao et al.

In the exciting generative AI era, the diffusion model has emerged as a very powerful and widely adopted content generation and editing tool for various data modalities, making the study of their potential security risks very necessary and critical. Very recently, some pioneering works have shown the vulnerability of the diffusion model against backdoor attacks, calling for in-depth analysis and investigation of the security challenges of this popular and fundamental AI technique. In this paper, for the first time, we systematically explore the detectability of the poisoned noise input for the backdoored diffusion models, an important performance metric yet little explored in the existing works. Starting from the perspective of a defender, we first analyze the properties of the trigger pattern in the existing diffusion backdoor attacks, discovering the important role of distribution discrepancy in Trojan detection. Based on this finding, we propose a low-cost trigger detection mechanism that can effectively identify the poisoned input noise. We then take a further step to study the same problem from the attack side, proposing a backdoor attack strategy that can learn the unnoticeable trigger to evade our proposed detection scheme. Empirical evaluations across various diffusion models and datasets demonstrate the effectiveness of the proposed trigger detection and detection-evading attack strategy. For trigger detection, our distribution discrepancy-based solution can achieve a 100\% detection rate for the Trojan triggers used in the existing works. For evading trigger detection, our proposed stealthy trigger design approach performs end-to-end learning to make the distribution of poisoned noise input approach that of benign noise, enabling nearly 100\% detection pass rate with very high attack and benign performance for the backdoored diffusion models.

Jinqi Xiao, Shen Sang, Tiancheng Zhi et al.

Training large-scale neural networks in vision, and multimodal domains demands substantial memory resources, primarily due to the storage of optimizer states. While LoRA, a popular parameter-efficient method, reduces memory usage, it often suffers from suboptimal performance due to the constraints of low-rank updates. Low-rank gradient projection methods (e.g., GaLore, Flora) reduce optimizer memory by projecting gradients and moment estimates into low-rank spaces via singular value decomposition or random projection. However, they fail to account for inter-projection correlation, causing performance degradation, and their projection strategies often incur high computational costs. In this paper, we present COAP (Correlation-Aware Gradient Projection), a memory-efficient method that minimizes computational overhead while maintaining training performance. Evaluated across various vision, language, and multimodal tasks, COAP outperforms existing methods in both training speed and model performance. For LLaMA-1B, it reduces optimizer memory by 61% with only 2% additional time cost, achieving the same PPL as AdamW. With 8-bit quantization, COAP cuts optimizer memory by 81% and achieves 4x speedup over GaLore for LLaVA-v1.5-7B fine-tuning, while delivering higher accuracy.

Bo Yuan, Jiazi Hu

Course evaluation is a critical component in higher education pedagogy. It not only serves to identify limitations in existing course designs and provide a basis for curricular innovation, but also to offer quantitative insights for university administrative decision-making. Traditional evaluation methods, primarily comprising student surveys, instructor self-assessments, and expert reviews, often encounter challenges, including inherent subjectivity, feedback delays, inefficiencies, and limitations in addressing innovative teaching approaches. Recent advancements in large language models (LLMs) within artificial intelligence (AI) present promising new avenues for enhancing course evaluation processes. This study explores the application of LLMs in automated course evaluation from multiple perspectives and conducts rigorous experiments across 100 courses at a major university in China. The findings indicate that: (1) LLMs can be an effective tool for course evaluation; (2) their effectiveness is contingent upon appropriate fine-tuning and prompt engineering; and (3) LLM-generated evaluation results demonstrate a notable level of rationality and interpretability.

Qingquan Zhang, Ziqi Wang, Yuchen Li et al.

In recent years, the generation of diverse game levels has gained increasing interest, contributing to a richer and more engaging gaming experience. A number of level diversity metrics have been proposed in literature, which are naturally multi-dimensional, leading to conflicted, complementary, or both relationships among these dimensions. However, existing level generation approaches often fail to comprehensively assess diversity across those dimensions. This paper aims to expand horizons of level diversity by considering multi-dimensional diversity when training generative models. We formulate the model training as a multi-objective learning problem, where each diversity metric is treated as a distinct objective. Furthermore, a multi-objective evolutionary learning framework that optimises multiple diversity metrics simultaneously throughout the model training process is proposed. Our case study on the commonly used benchmark Super Mario Bros. demonstrates that our proposed framework can enhance multi-dimensional diversity and identify a Pareto front of generative models, which provides a range of tradeoffs among playability and two representative diversity metrics, including a content-based one and a player-centered one. Such capability enables decision-makers to make informed choices when selecting generators accommodating a variety of scenarios and the diverse needs of players and designers.

Bo Yuan, Jiazi Hu

Over the past decade, higher education has evolved through three distinct paradigms: the emergence of Massive Open Online Courses (MOOCs), the integration of Smart Teaching technologies into classrooms, and the rise of AI-enhanced learning. Each paradigm is intended to address specific challenges in traditional education: MOOCs enable ubiquitous access to learning resources; Smart Teaching supports real-time interaction with data-driven insights; and generative AI offers personalized feedback and on-demand content generation. However, these paradigms are often implemented in isolation due to their disparate technological origins and policy-driven adoption. This paper examines the origins, strengths, and limitations of each paradigm, and advocates a unified pedagogical perspective that synthesizes their complementary affordances. We propose a three-layer instructional framework that combines the scalability of MOOCs, the responsiveness of Smart Teaching, and the adaptivity of AI. To demonstrate its feasibility, we present a curriculum design for a project-based course. The findings highlight the framework's potential to enhance learner engagement, support instructors, and enable personalized yet scalable learning.

Yang Sui, Yanyu Li, Anil Kag et al.

Diffusion-based image generation models have achieved great success in recent years by showing the capability of synthesizing high-quality content. However, these models contain a huge number of parameters, resulting in a significantly large model size. Saving and transferring them is a major bottleneck for various applications, especially those running on resource-constrained devices. In this work, we develop a novel weight quantization method that quantizes the UNet from Stable Diffusion v1.5 to 1.99 bits, achieving a model with 7.9X smaller size while exhibiting even better generation quality than the original one. Our approach includes several novel techniques, such as assigning optimal bits to each layer, initializing the quantized model for better performance, and improving the training strategy to dramatically reduce quantization error. Furthermore, we extensively evaluate our quantized model across various benchmark datasets and through human evaluation to demonstrate its superior generation quality.

Bo Xia, Yilun Kong, Yongzhe Chang et al.

Classic reinforcement learning (RL) frequently confronts challenges in tasks involving delays, which cause a mismatch between received observations and subsequent actions, thereby deviating from the Markov assumption. Existing methods usually tackle this issue with end-to-end solutions using state augmentation. However, these black-box approaches often involve incomprehensible processes and redundant information in the information states, causing instability and potentially undermining the overall performance. To alleviate the delay challenges in RL, we propose $\textbf{DEER (Delay-resilient Encoder-Enhanced RL)}$, a framework designed to effectively enhance the interpretability and address the random delay issues. DEER employs a pretrained encoder to map delayed states, along with their variable-length past action sequences resulting from different delays, into hidden states, which is trained on delay-free environment datasets. In a variety of delayed scenarios, the trained encoder can seamlessly integrate with standard RL algorithms without requiring additional modifications and enhance the delay-solving capability by simply adapting the input dimension of the original algorithms. We evaluate DEER through extensive experiments on Gym and Mujoco environments. The results confirm that DEER is superior to state-of-the-art RL algorithms in both constant and random delay settings.

Yifan Shi, Kang Wei, Li Shen et al.

Federated learning (FL) is a collaborative learning paradigm for decentralized private data from mobile terminals (MTs). However, it suffers from issues in terms of communication, resource of MTs, and privacy. Existing privacy-preserving FL methods usually adopt the instance-level differential privacy (DP), which provides a rigorous privacy guarantee but with several bottlenecks: severe performance degradation, transmission overhead, and resource constraints of edge devices such as MTs. To overcome these drawbacks, we propose Fed-LTP, an efficient and privacy-enhanced FL framework with \underline{\textbf{L}}ottery \underline{\textbf{T}}icket \underline{\textbf{H}}ypothesis (LTH) and zero-concentrated D\underline{\textbf{P}} (zCDP). It generates a pruned global model on the server side and conducts sparse-to-sparse training from scratch with zCDP on the client side. On the server side, two pruning schemes are proposed: (i) the weight-based pruning (LTH) determines the pruned global model structure; (ii) the iterative pruning further shrinks the size of the pruned model's parameters. Meanwhile, the performance of Fed-LTP is also boosted via model validation based on the Laplace mechanism. On the client side, we use sparse-to-sparse training to solve the resource-constraints issue and provide tighter privacy analysis to reduce the privacy budget. We evaluate the effectiveness of Fed-LTP on several real-world datasets in both independent and identically distributed (IID) and non-IID settings. The results clearly confirm the superiority of Fed-LTP over state-of-the-art (SOTA) methods in communication, computation, and memory efficiencies while realizing a better utility-privacy trade-off.

Yifan Shi, Kang Wei, Li Shen et al.

To defend the inference attacks and mitigate the sensitive information leakages in Federated Learning (FL), client-level Differentially Private FL (DPFL) is the de-facto standard for privacy protection by clipping local updates and adding random noise. However, existing DPFL methods tend to make a sharp loss landscape and have poor weight perturbation robustness, resulting in severe performance degradation. To alleviate these issues, we propose a novel DPFL algorithm named DP-FedSAM, which leverages gradient perturbation to mitigate the negative impact of DP. Specifically, DP-FedSAM integrates Sharpness Aware Minimization (SAM) optimizer to generate local flatness models with improved stability and weight perturbation robustness, which results in the small norm of local updates and robustness to DP noise, thereby improving the performance. To further reduce the magnitude of random noise while achieving better performance, we propose DP-FedSAM-$top_k$ by adopting the local update sparsification technique. From the theoretical perspective, we present the convergence analysis to investigate how our algorithms mitigate the performance degradation induced by DP. Meanwhile, we give rigorous privacy guarantees with Rényi DP, the sensitivity analysis of local updates, and generalization analysis. At last, we empirically confirm that our algorithms achieve state-of-the-art (SOTA) performance compared with existing SOTA baselines in DPFL.

Zhecheng Yuan, Guozheng Ma, Yao Mu et al.

One of the key challenges in visual Reinforcement Learning (RL) is to learn policies that can generalize to unseen environments. Recently, data augmentation techniques aiming at enhancing data diversity have demonstrated proven performance in improving the generalization ability of learned policies. However, due to the sensitivity of RL training, naively applying data augmentation, which transforms each pixel in a task-agnostic manner, may suffer from instability and damage the sample efficiency, thus further exacerbating the generalization performance. At the heart of this phenomenon is the diverged action distribution and high-variance value estimation in the face of augmented images. To alleviate this issue, we propose Task-aware Lipschitz Data Augmentation (TLDA) for visual RL, which explicitly identifies the task-correlated pixels with large Lipschitz constants, and only augments the task-irrelevant pixels. To verify the effectiveness of TLDA, we conduct extensive experiments on DeepMind Control suite, CARLA and DeepMind Manipulation tasks, showing that TLDA improves both sample efficiency in training time and generalization in test time. It outperforms previous state-of-the-art methods across the 3 different visual control benchmarks.

Yulin Chen, Beishui Liao, Bruno Bentzen et al.

As one of the basic tasks in natural language processing (NLP), named entity recognition (NER) is an important basic tool for downstream tasks of NLP, such as information extraction, syntactic analysis, machine translation and so on. The internal operation logic of current name entity recognition model is black-box to the user, so the user has no basis to determine which name entity makes more sense. Therefore, a user-friendly explainable recognition process would be very useful for many people. In this paper, we propose a novel interpretable method, BTPK (Binary Talmudic Public Announcement Logic model), to help users understand the internal recognition logic of the name entity recognition tasks based on Talmudic Public Announcement Logic. BTPK model can also capture the semantic information in the input sentences, that is, the context dependency of the sentence. We observed the public announcement of BTPK presents the inner decision logic of BRNNs, and the explanations obtained from a BTPK model show us how BRNNs essentially handle NER tasks.

Yuxing Wang, Tiantian Zhang, Yongzhe Chang et al.

The integration of Reinforcement Learning (RL) and Evolutionary Algorithms (EAs) aims at simultaneously exploiting the sample efficiency as well as the diversity and robustness of the two paradigms. Recently, hybrid learning frameworks based on this principle have achieved great success in various challenging robot control tasks. However, in these methods, policies from the genetic population are evaluated via interactions with the real environments, limiting their applicability in computationally expensive problems. In this work, we propose Surrogate-assisted Controller (SC), a novel and efficient module that can be integrated into existing frameworks to alleviate the computational burden of EAs by partially replacing the expensive policy evaluation. The key challenge in applying this module is to prevent the optimization process from being misled by the possible false minima introduced by the surrogate. To address this issue, we present two strategies for SC to control the workflow of hybrid frameworks. Experiments on six continuous control tasks from the OpenAI Gym platform show that SC can not only significantly reduce the cost of fitness evaluations, but also boost the performance of the original hybrid frameworks with collaborative learning and evolutionary processes.

Yang Liu, Yongzhe Chang, Shilei Jiang et al.

Imitation Learning (IL) is an effective learning paradigm exploiting the interactions between agents and environments. It does not require explicit reward signals and instead tries to recover desired policies using expert demonstrations. In general, IL methods can be categorized into Behavioral Cloning (BC) and Inverse Reinforcement Learning (IRL). In this work, a novel reward function based on probability density estimation is proposed for IRL, which can significantly reduce the complexity of existing IRL methods. Furthermore, we prove that the theoretically optimal policy derived from our reward function is identical to the expert policy as long as it is deterministic. Consequently, an IRL problem can be gracefully transformed into a probability density estimation problem. Based on the proposed reward function, we present a "watch-try-learn" style framework named Probability Density Estimation based Imitation Learning (PDEIL), which can work in both discrete and continuous action spaces. Finally, comprehensive experiments in the Gym environment show that PDEIL is much more efficient than existing algorithms in recovering rewards close to the ground truth.

Chengqian Gao, Ke Xu, Kuangqi Zhou et al.

Scaling reinforcement learning (RL) to recommender systems (RS) is promising since maximizing the expected cumulative rewards for RL agents meets the objective of RS, i.e., improving customers' long-term satisfaction. A key approach to this goal is offline RL, which aims to learn policies from logged data. However, the high-dimensional action space and the non-stationary dynamics in commercial RS intensify distributional shift issues, making it challenging to apply offline RL methods to RS. To alleviate the action distribution shift problem in extracting RL policy from static trajectories, we propose Value Penalized Q-learning (VPQ), an uncertainty-based offline RL algorithm. It penalizes the unstable Q-values in the regression target by uncertainty-aware weights, without the need to estimate the behavior policy, suitable for RS with a large number of items. We derive the penalty weights from the variances across an ensemble of Q-functions. To alleviate distributional shift issues at test time, we further introduce the critic framework to integrate the proposed method with classic RS models. Extensive experiments conducted on two real-world datasets show that the proposed method could serve as a gain plugin for existing RS models.

Hua Wei, Deheng Ye, Zhao Liu et al.

Offline reinforcement learning (RL) tries to learn the near-optimal policy with recorded offline experience without online exploration. Current offline RL research includes: 1) generative modeling, i.e., approximating a policy using fixed data; and 2) learning the state-action value function. While most research focuses on the state-action function part through reducing the bootstrapping error in value function approximation induced by the distribution shift of training data, the effects of error propagation in generative modeling have been neglected. In this paper, we analyze the error in generative modeling. We propose AQL (action-conditioned Q-learning), a residual generative model to reduce policy approximation error for offline RL. We show that our method can learn more accurate policy approximations in different benchmark datasets. In addition, we show that the proposed offline RL method can learn more competitive AI agents in complex control tasks under the multiplayer online battle arena (MOBA) game Honor of Kings.

Liang Xu, Liying Zheng, Weijun Li et al.

In recent studies, Lots of work has been done to solve time series anomaly detection by applying Variational Auto-Encoders (VAEs). Time series anomaly detection is a very common but challenging task in many industries, which plays an important role in network monitoring, facility maintenance, information security, and so on. However, it is very difficult to detect anomalies in time series with high accuracy, due to noisy data collected from real world, and complicated abnormal patterns. From recent studies, we are inspired by Nouveau VAE (NVAE) and propose our anomaly detection model: Time series to Image VAE (T2IVAE), an unsupervised model based on NVAE for univariate series, transforming 1D time series to 2D image as input, and adopting the reconstruction error to detect anomalies. Besides, we also apply the Generative Adversarial Networks based techniques to T2IVAE training strategy, aiming to reduce the overfitting. We evaluate our model performance on three datasets, and compare it with other several popular models using F1 score. T2IVAE achieves 0.639 on Numenta Anomaly Benchmark, 0.651 on public dataset from NASA, and 0.504 on our dataset collected from real-world scenario, outperforms other comparison models.

Li Zhong, Zhen Fang, Feng Liu et al.

Unsupervised domain adaptation (UDA) aims to train a target classifier with labeled samples from the source domain and unlabeled samples from the target domain. Classical UDA learning bounds show that target risk is upper bounded by three terms: source risk, distribution discrepancy, and combined risk. Based on the assumption that the combined risk is a small fixed value, methods based on this bound train a target classifier by only minimizing estimators of the source risk and the distribution discrepancy. However, the combined risk may increase when minimizing both estimators, which makes the target risk uncontrollable. Hence the target classifier cannot achieve ideal performance if we fail to control the combined risk. To control the combined risk, the key challenge takes root in the unavailability of the labeled samples in the target domain. To address this key challenge, we propose a method named E-MixNet. E-MixNet employs enhanced mixup, a generic vicinal distribution, on the labeled source samples and pseudo-labeled target samples to calculate a proxy of the combined risk. Experiments show that the proxy can effectively curb the increase of the combined risk when minimizing the source risk and distribution discrepancy. Furthermore, we show that if the proxy of the combined risk is added into loss functions of four representative UDA methods, their performance is also improved.

Yiyang Zhang, Feng Liu, Zhen Fang et al.

In unsupervised domain adaptation (UDA), a classifier for the target domain is trained with massive true-label data from the source domain and unlabeled data from the target domain. However, collecting fully-true-label data in the source domain is high-cost and sometimes impossible. Compared to the true labels, a complementary label specifies a class that a pattern does not belong to, hence collecting complementary labels would be less laborious than collecting true labels. Thus, in this paper, we propose a novel setting that the source domain is composed of complementary-label data, and a theoretical bound for it is first proved. We consider two cases of this setting, one is that the source domain only contains complementary-label data (completely complementary unsupervised domain adaptation, CC-UDA), and the other is that the source domain has plenty of complementary-label data and a small amount of true-label data (partly complementary unsupervised domain adaptation, PC-UDA). To this end, a complementary label adversarial network} (CLARINET) is proposed to solve CC-UDA and PC-UDA problems. CLARINET maintains two deep networks simultaneously, where one focuses on classifying complementary-label source data and the other takes care of source-to-target distributional adaptation. Experiments show that CLARINET significantly outperforms a series of competent baselines on handwritten-digits-recognition and objects-recognition tasks.

Yiyang Zhang, Feng Liu, Zhen Fang et al.

In unsupervised domain adaptation (UDA), classifiers for the target domain are trained with massive true-label data from the source domain and unlabeled data from the target domain. However, it may be difficult to collect fully-true-label data in a source domain given a limited budget. To mitigate this problem, we consider a novel problem setting where the classifier for the target domain has to be trained with complementary-label data from the source domain and unlabeled data from the target domain named budget-friendly UDA (BFUDA). The key benefit is that it is much less costly to collect complementary-label source data (required by BFUDA) than collecting the true-label source data (required by ordinary UDA). To this end, the complementary label adversarial network (CLARINET) is proposed to solve the BFUDA problem. CLARINET maintains two deep networks simultaneously, where one focuses on classifying complementary-label source data and the other takes care of the source-to-target distributional adaptation. Experiments show that CLARINET significantly outperforms a series of competent baselines.

Li Zhong, Zhen Fang, Feng Liu et al.

In the unsupervised open set domain adaptation (UOSDA), the target domain contains unknown classes that are not observed in the source domain. Researchers in this area aim to train a classifier to accurately: 1) recognize unknown target data (data with unknown classes) and, 2) classify other target data. To achieve this aim, a previous study has proven an upper bound of the target-domain risk, and the open set difference, as an important term in the upper bound, is used to measure the risk on unknown target data. By minimizing the upper bound, a shallow classifier can be trained to achieve the aim. However, if the classifier is very flexible (e.g., deep neural networks (DNNs)), the open set difference will converge to a negative value when minimizing the upper bound, which causes an issue where most target data are recognized as unknown data. To address this issue, we propose a new upper bound of target-domain risk for UOSDA, which includes four terms: source-domain risk, $ε$-open set difference ($Δ_ε$), a distributional discrepancy between domains, and a constant. Compared to the open set difference, $Δ_ε$ is more robust against the issue when it is being minimized, and thus we are able to use very flexible classifiers (i.e., DNNs). Then, we propose a new principle-guided deep UOSDA method that trains DNNs via minimizing the new upper bound. Specifically, source-domain risk and $Δ_ε$ are minimized by gradient descent, and the distributional discrepancy is minimized via a novel open-set conditional adversarial training strategy. Finally, compared to existing shallow and deep UOSDA methods, our method shows the state-of-the-art performance on several benchmark datasets, including digit recognition (MNIST, SVHN, USPS), object recognition (Office-31, Office-Home), and face recognition (PIE).

Xiao Zang, Yi Xie, Jie Chen et al.

Deep neural networks, while generalize well, are known to be sensitive to small adversarial perturbations. This phenomenon poses severe security threat and calls for in-depth investigation of the robustness of deep learning models. With the emergence of neural networks for graph structured data, similar investigations are urged to understand their robustness. It has been found that adversarially perturbing the graph structure and/or node features may result in a significant degradation of the model performance. In this work, we show from a different angle that such fragility similarly occurs if the graph contains a few bad-actor nodes, which compromise a trained graph neural network through flipping the connections to any targeted victim. Worse, the bad actors found for one graph model severely compromise other models as well. We call the bad actors ``anchor nodes'' and propose an algorithm, named GUA, to identify them. Thorough empirical investigations suggest an interesting finding that the anchor nodes often belong to the same class; and they also corroborate the intuitive trade-off between the number of anchor nodes and the attack success rate. For the dataset Cora which contains 2708 nodes, as few as six anchor nodes will result in an attack success rate higher than 80\% for GCN and other three models.

Rayan Mosli, Matthew Wright, Bo Yuan et al.

Machine learning models have been found to be susceptible to adversarial examples that are often indistinguishable from the original inputs. These adversarial examples are created by applying adversarial perturbations to input samples, which would cause them to be misclassified by the target models. Attacks that search and apply the perturbations to create adversarial examples are performed in both white-box and black-box settings, depending on the information available to the attacker about the target. For black-box attacks, the only capability available to the attacker is the ability to query the target with specially crafted inputs and observing the labels returned by the model. Current black-box attacks either have low success rates, requires a high number of queries, or produce adversarial examples that are easily distinguishable from their sources. In this paper, we present AdversarialPSO, a black-box attack that uses fewer queries to create adversarial examples with high success rates. AdversarialPSO is based on the evolutionary search algorithm Particle Swarm Optimization, a populationbased gradient-free optimization algorithm. It is flexible in balancing the number of queries submitted to the target vs the quality of imperceptible adversarial examples. The attack has been evaluated using the image classification benchmark datasets CIFAR-10, MNIST, and Imagenet, achieving success rates of 99.6%, 96.3%, and 82.0%, respectively, while submitting substantially fewer queries than the state-of-the-art. We also present a black-box method for isolating salient features used by models when making classifications. This method, called Swarms with Individual Search Spaces or SWISS, creates adversarial examples by finding and modifying the most important features in the input.

Tiantian Zhang, Li Zhong, Bo Yuan

Experimental evaluation is a major research methodology for investigating clustering algorithms and many other machine learning algorithms. For this purpose, a number of benchmark datasets have been widely used in the literature and their quality plays a key role on the value of the research work. However, in most of the existing studies, little attention has been paid to the properties of the datasets and they are often regarded as black-box problems. For example, it is common to use datasets intended for classification in clustering research and assume class la-bels as the ground truth for judging the quality of cluster-ing. In our work, with the help of advanced visualization and dimension reduction techniques, we show that this practice may seriously compromise the research quality and produce misleading results. We suggest that the applicability of existing benchmark datasets should be carefully revisited and significant efforts need to be devoted to improving the current practice of experimental evaluation of clustering algorithms to ensure an essential match between algorithms and problems.

Liang Zhao, Siyu Liao, Yanzhi Wang et al.

Recently low displacement rank (LDR) matrices, or so-called structured matrices, have been proposed to compress large-scale neural networks. Empirical results have shown that neural networks with weight matrices of LDR matrices, referred as LDR neural networks, can achieve significant reduction in space and computational complexity while retaining high accuracy. We formally study LDR matrices in deep learning. First, we prove the universal approximation property of LDR neural networks with a mild condition on the displacement operators. We then show that the error bounds of LDR neural networks are as efficient as general neural networks with both single-layer and multiple-layer structure. Finally, we propose back-propagation based training algorithm for general LDR neural networks.