论文检索

Shuangyin Li, Jihua Yang, Yixuan Wang, Shimin Di, Lei Chen 0002

Single-cell RNA sequencing (scRNA-seq) technology has emerged as a powerful tool for studying complex biological systems and diseases with high resolution. However, generating sufficient high quality scRNA-seq samples for accurate downstream analyses and ensuring reproducibility remains a challenge. Previous methods often produce low-quality samples or a limited number of useful specific cell subpopulations. To address this issue, we propose a novel Efficient Single-Cell RNA-seq Flow Diffusion (named ESCFD) method based on the Diffusion Model, capable of synthesizing large-scale, high-quality scRNA-seq samples and generating either ''holistic'' or specific cellular subpopulations within a single framework. A pre-guidance mechanism is designed for synthesizing specific cellular subpopulations of high quality, and a post-guidance mechanism was designed to accelerate the sampling of scRNA-seq samples. The ESCFD can efficiently synthesize large-scale and high-quality scRNA-seq samples for various downstream tasks, surpassing previous work with faster sampling speed. Experimental results demonstrate that the ESCFD model achieves state-of-the-art performance in cell classification and cell distribution similarity when evaluated on three scRNA-seq benchmarks, and verified the effectiveness of accelerated sampling. Visualization experiments also reveal the ESCFD's ability to synthesize specific cellular subpopulations. This innovative approach has the potential to significantly advance our understanding of complex biological systems and accelerate the development of novel therapeutic interventions and personalized medicine strategies.

Ruikun Li 0001, Ye Xiao, Xiaoxiao Ma 0002, Andrey Vasnev, Junbin Gao

A significant challenge for Graph Neural Networks (GNNs) lies in accurately performing node classification tasks on heterophilous graphs. Traditional GNN models, which largely rely on the assumption of homophily, often struggle under heterophilous conditions due to the inherent low-pass filtering nature during message-passing among neighboring nodes. Motivated by these limitations, our research explores the dendritic structures found in real neurons, which dynamically amplify and inhibit signals. We demonstrate how the biophysical properties of dendrites enable GNNs to adaptively modulate the Dirichlet energy of graph representations based on the specific context, providing a theoretical justification for integrating neural dendrites into GNNs to improve learning on heterophilous graphs. In this work, we introduce the GDendrite framework, which dynamically adjusts GNN's output response to the various contexts. Our empirical studies, conducted across 13 homophilous and heterophilous benchmark datasets, show that our framework significantly enhances the performance of traditional GNNs in heterophilous settings and outperforms state-of-the-art models in most cases.

Ruikun Li 0002, Jingwen Cheng, Huandong Wang, Qingmin Liao, Yong Li 0008

Predicting the dynamics of complex systems is crucial for various scientific and engineering applications. The accuracy of predictions depends on the model's ability to capture the intrinsic dynamics. While existing methods capture key dynamics by encoding a low-dimensional latent space, they overlook the inherent multiscale structure of complex systems, making it difficult to accurately predict complex spatiotemporal evolution. Therefore, we propose a Multiscale Diffusion Prediction Network (MDPNet) that leverages the multiscale structure of complex systems to discover the latent space of intrinsic dynamics. First, we encode multiscale features through a multiscale diffusion autoencoder to guide the diffusion model for reliable reconstruction. Then, we introduce an attention-based graph neural ordinary differential equation to model the co-evolution across different scales. Extensive evaluations on representative systems demonstrate that the proposed method achieves an average prediction error reduction of 53.23% compared to baselines, while also exhibiting superior robustness and generalization.

Ruifeng Li 0002, Mingqian Li, Wei Liu, Hongyang Chen 0001

Effective molecular representation learning is crucial for advancing molecular property prediction and drug design. Mainstream molecular representation learning methods rely on Graph Neural Networks (GNNs) to model complex molecular structures. However, these GNN-based approaches struggle with three significant issues: insufficient annotations, molecular diversity, and architectural limitations such as over-squashing, which leads to the loss of critical structural details. To address these issues, we introduce a new class of GNNs that integrates the Kolmogorov-Arnold Networks (KANs), known for their robust data-fitting capabilities and high accuracy in small-scale AI + Science tasks. By incorporating KANs into GNNs, our model enhances the representation of molecular structures. We further advance this approach with a variant called SwallowKAN (SKAN), which employs adaptive Radial Basis Functions (RBFs) as the core of the non-linear neurons. This innovation improves both computational efficiency and adaptability to diverse molecular structures. Building on the strengths of SKAN, we propose a new class of GNNs, GNN-SKAN, and its augmented variant, GNN-SKAN+, which incorporates a SKAN-based classifier to further boost the performance. Experiments across 6 classification datasets, 6 regression datasets, and 4 few-shot learning datasets demonstrate that our approach achieves new state-of-the-art performance in terms of accuracy and computational cost.

Rui Li 0086, Quanyu Dai, Zeyu Zhang 0007, Xu Chen 0017, Zhenhua Dong, Ji-Rong Wen

Recent advances in retrieval-augmented generation (RAG) furnish large language models (LLMs) with iterative retrievals of relevant information to handle complex multi-hop questions. These methods typically alternate between LLM reasoning and retrieval to accumulate external information into the LLM's context. However, the ever-growing context inherently imposes an increasing burden on the LLM to perceive connections among critical information pieces, with futile reasoning steps further exacerbating this overload issue. In this paper, we present KnowTrace, an elegant RAG framework to (1) mitigate the context overload and (2) bootstrap higher-quality multi-step reasoning. Instead of simply piling the retrieved contents, KnowTrace autonomously traces out desired knowledge triplets to organize a specific knowledge graph relevant to the input question. Such a structured workflow not only empowers the LLM with an intelligible context for inference, but also naturally inspires a reflective mechanism of knowledge backtracing to identify contributive LLM generations as process supervision data for self-bootstrapping. Extensive experiments show that KnowTrace consistently surpasses existing methods across three multi-hop question answering benchmarks, and the bootstrapped version further amplifies the gains.

Peiwen Li, Xin Wang 0019, Zeyang Zhang 0001, Ziwei Zhang 0001, Fang Shen, Jialong Wang 0001, Yang Li 0104, Wenwu Zhu 0001

Graph neural architecture search (NAS) has emerged as a promising approach for autonomously designing graph neural network architectures by leveraging correlations between graphs and architectures. However, existing methods merely rely on correlations, which may be spurious and vary across distributions. This reliance, without considering causal graph-architecture relationships, limits their ability to generalize under distribution shifts that are ubiquitous in real-world graph scenarios. In this paper, we propose to handle the distribution shifts in NAS process by exploiting the causal graph-architecture relationship to search for optimal architectures that can generalize under distribution shifts. Key challenges remain unexplored: discovering causal graph-architecture relationships with stable cross-distribution predictive abilities, and leveraging them to handle distribution shifts. To address these challenges, we propose a novel approach, Causal-aware Graph Neural Architecture Search (CARNAS), which is capable of capturing causal graph-architecture relationship during NAS process and discovering optimal graph architecture under distribution shifts. We propose Disentangled Causal Subgraph Identification to extract causal subgraphs with stable predictive power across distributions, followed by Graph Embedding Intervention to intervene on these subgraphs in latent space by preserving essential features while filtering out non-causal elements, and Invariant Architecture Customization to enhance their causal invariance for optimizing graph architectures. Extensive experiments on synthetic and real-world datasets show that CARNAS enhances out-of-distribution generalization by uncovering causal graph-architecture relationships during NAS.

Ningyuan Li 0001, Zhilin Zhang 0003, Tianyan Long, Yuyao Liu, Rongquan Bai, Yurong Chen 0002, Xiaotie Deng, Pengjie Wang 0002, Chuan Yu 0002, Jian Xu 0015 等

On e-commerce platforms, sellers typically bid for impressions from ad traffic to promote their products. However, for most sellers, the majority of their sales come from organic traffic. Consequently, the relationship between their ad spending and total sales remains uncertain, resulting in operational inefficiency. To address this issue, e-commerce platforms have recently introduced a novel platform-wide marketing service known as QuanZhanTui, which has reportedly enhanced marketing efficiency for sellers and driven substantial revenue growth for platforms. QuanZhanTui allows sellers to bid for impressions from the platform's entire traffic to boost their total sales without compromising the platform's user experience. In this paper, we investigate the mechanism design problem that arises from QuanZhanTui. The problem is formulated as a multi-objective optimization to balance sellers' welfare and platform's user experience. We first introduce the stock-constrained value maximizer model, which reflects sellers' dual requirements on marketing efficiency and platform-wide ROI. Then, we propose the Liquid Payment Auction (LPA), an auction designed to optimize the balanced objectives while accounting for sellers' requirements in the auto-bidding environment. It employs a simple payment rule based on sellers' liquid welfare, providing a clearer link between their investment and total sales. Under mild assumptions, we theoretically prove desirable properties of LPA, such as optimality and incentive compatibility. Extensive experiments demonstrate LPA's superior performance over conventional auctions in QuanZhanTui.

Mingjia Li 0002, Junkai Tong, Yiyang Huang, Yifei Ding, Hong Qian, Aimin Zhou

Computerized Adaptive Testing (CAT) is a testing technique that accurately infers students' proficiency levels using a relatively small number of questions. Most existing CAT systems operate on a question-level adaptive paradigm, which is suitable for practice scenarios. However, in computerized standardized high-stakes examinations such as the GRE and GMAT, this paradigm faces several challenges: (1) the lack of comparability in exam results(2) high implementation costs due to the reliance on real-time interactions and the financial burden of maintaining CAT testing system, and (3) the difficulty in balancing multiple factors of diagnosis quality, attribute coverage, and question exposure. To address these challenges, we propose a Paper-level Computerized Adaptive Testing (PCAT) and its corresponding evaluation method. PCAT divides an exam into multiple testing stages, where examinees adaptively receive test papers of varying difficulty based on their performance in previous stages. The paper assembly problem in PCAT is solved using a population-based multi-objective optimization (MOO) approach. PCAT offers several advantages: First, the paper-level adaptive mechanism ensures that the questions faced by examinees depend solely on their performance in the earlier stages, maintaining adaptability while enhancing the comparability of results across different examinees. Second, PCAT replaces the selection strategy module in traditional CAT with an assembly module, allowing computationally intensive tasks such as cognitive diagnosis and paper assembly to be completed offline before the exam, eliminating the need for real-time interactions. Additionally, the population-based MOO approach generates a set of high-quality solutions in one run, meeting the demands of frequent administration of standardized high-stakes exams like the GRE and reducing the financial burden of maintaining a large-scale CAT system. Finally, MOO naturally models multiple factors as separate objectives, enabling a balanced consideration of these factors and allowing exam administrators to customize the exam based on specific needs. Extensive experiments on four real-world datasets show that PCAT outperforms state-of-the-art (SOTA) CAT methods in terms of diagnosis quality, attribute coverage, and question exposure, while maintaining the same number of questions answered by examinees. These results highlight PCAT's potential in high-stakes examination settings.

Ke Li 0019, Lisi Chen 0001, Shuo Shang, Christian S. Jensen, Panos Kalnis

With the proliferation of GPS-enabled devices such as smartphones, the querying of moving objects has attracted substantial attention, with studies covering joins, range and kNN queries, similarity queries, etc. Challenges arise due to variable sampling frequencies, potential inaccuracies in location samples, and the unavailability of locations between samples. Existing similarity joins often rely on discrete location samples, which fail to capture movement uncertainty and may miss meaningful interactions. To address this limitation, we propose Intersection Similarity Join (IS-Join), a novel approach that identifies object pairs based on the overlap of their motion ranges rather than location-based proximity. We define motion ranges as the spatial regions an object may traverse within a given time period, and introduce an intersection similarity measure that quantifies their overlap. To efficiently process IS-Join queries, we develop a Hybrid Ball-tree indexing structure with a repartitioning strategy, enabling scalable candidate filtering. Additionally, we introduce pre-checking and pruning techniques to further reduce computational overhead. Extensive experiments on two real-world trajectory datasets demonstrate that IS-Join significantly outperforms well-designed baselines, achieving up to a 3x reduction in runtime. Our work opens new opportunities for applications such as urban mobility analysis, traffic monitoring, wildlife tracking, and contact tracing.

Juren Li, Yang Yang 0009, Hanchen Su, Jiayu Liu, Youmin Chen, Jianfeng Zhang, Lujia Pan

Current deep learning approaches for lithium-ion battery analysis are often specialized and limited to specific battery types or individual tasks. While recent advances in large language models (LLMs) highlight the potential of pretraining paradigms, existing time-series pretraining models inadequately address the physicochemical complexity and temporal irregularity inherent to battery operational data. We propose LiPM, a pretrained foundation model that unifies multi-dataset learning through physics-aware objectives and irregularity-tolerant temporal modeling. LiPM introduces three key innovations: (1) A Mix-Masked Autoencoder (MMAE) enforcing electrochemical consistency via joint reconstruction of temporally masked patches and cross-channel masked variables(2) A Coulombic Integration Regression (CIR) task explicitly encoding charge conservation laws, and (3) A dual-scale temporal encoder combining irregular intra-patch processing (preserving raw timestamps) with regular inter-patch attention (capturing macroscopic dynamics). Trained on eight heterogeneous battery datasets without cycle-label annotations, LiPM demonstrates universal applicability across partial charge-discharge segments and irregular sampling protocols. Extensive experiments show remarkable improvements over 9 state-of-the-art baselines in critical downstream tasks.

Junjun Li, Zeyuan Ma, Ting Huang 0001, Yue-Jiao Gong

Lifelong Multi-Agent Path Finding (LMAPF) focuses on planning conflict-free paths for agents, like autonomous vehicles, that are continuously assigned new tasks. The synergy of search-based and learning-based methods holds promise for striking a balance in-between effectiveness and efficiency but still faces several challenges such as inferior initial paths, weak search-learning synergy and low sample utilization rate. To address these issues, this paper proposes a new synergized LMAPF approach, named Synergistic Multi-Agent Path Optimization (SMAPO), which consists of two tightly-coupled phases: Primordial Planning and Decision Refinement. In the Primordial Planning phase, we introduce a novel load-balanced A* algorithm that integrates planned and perceived congestion costs, which enhances initial solution quality by evenly distributing spatiotemporal traffic loads, thereby mitigating potential conflicts. In the Decision Refinement phase, we propose a novel Encoder-Decoder based neural network to learn a collaborative optimization policy through multi-agent reinforcement learning. In addition, we leverage dual transformations to augment trajectory samples during online learning, enhancing both the sample utilization rate and overall learning stability. Extensive experiments reveal that our SMAPO is superior to the state-of-the-art baselines in effectiveness, efficiency, and generalization capability. Source code is available at https://github.com/ByteUser-blues/SMAPO.

Jinning Li 0001, Ruipeng Han, Jingying Zeng, Dachun Sun, Chenkai Sun, Hanghang Tong, ChengXiang Zhai, Boleslaw K. Szymanski, Tarek F. Abdelzaher

The perceptions and decisions of individuals on social networks are deeply rooted in their intrinsic beliefs, which makes it possible to infer social beliefs from user behavior and message interactions. While existing research models these interactions as graphs and learns their representations, interpretability remains a significant challenge. In real-world scenarios, the interpretation of beliefs is nested within subject scopes of different granularity (such as topics and locations), posing additional challenges for belief discovery. In this paper, we introduce the Interpretable Graph Auto-Encoder Tree (IGAT), a novel end-to-end framework that jointly encodes hierarchical subject scopes and corresponding beliefs as a unified, interpretable hierarchical representation. IGAT integrates the interpretable hierarchy of Model Trees with disentangled representation learning models. We propose a differentiable Slice Mechanism to dynamically optimize internal node splitting and jointly train a leaf model to learn disentangled belief subspaces. The aggregation of these subspaces yields a unified representation, offering interpretations for both subjects and beliefs. Experimental evaluations on three real-world Twitter datasets show that IGAT achieves a consistent improvement of 1.49%-5.61% in F1-score, accuracy, and purity in the belief discovery task, as well as its effectiveness in various downstream analytical applications.

Jian Li 0064, Han Wan, Ning Lin, Yu-Liang Zhan, Ruizhi Chengze, Haining Wang, Yi Zhang 0164, Hongsheng Liu 0002, Zidong Wang 0010, Fan Yu 0004 等

Understanding and reasoning about dynamics governed by physical laws through visual observation, akin to human capabilities in the real world, poses significant challenges. Currently, object-centric dynamic simulation methods, which emulate human behavior, have achieved notable progress but overlook two critical aspects: 1) the integration of physical knowledge into models. Humans gain physical insights by observing the world and apply this knowledge to accurately reason about various dynamic scenarios; 2) the validation of model adaptability across diverse scenarios. Real-world dynamics, especially those involving fluids and objects, demand models that not only capture object interactions but also simulate fluid flow characteristics. To address these gaps, we introduce SlotPi, a slot-based physics-informed object-centric reasoning model. SlotPi integrates a physical module based on Hamiltonian principles with a spatio-temporal prediction module for dynamic forecasting. Our experiments highlight the model's strengths in tasks such as prediction and Visual Question Answering (VQA) on benchmark and fluid datasets. Furthermore, we have created a real-world dataset encompassing object interactions, fluid dynamics, and fluid-object interactions, on which we validated our model's capabilities. The model's robust performance across all datasets underscores its strong adaptability, laying a foundation for developing more advanced world models.

Honghao Li, Yiwen Zhang 0001, Yi Zhang 0103, Lei Sang 0001, Jieming Zhu

Hadamard Product (HP) has long been a cornerstone in click-through rate (CTR) prediction tasks due to its simplicity, effectiveness, and ability to capture feature interactions without additional parameters. However, the underlying reasons for its effectiveness remain unclear. In this paper, we revisit HP from the perspective of Quadratic Neural Networks (QNN), which leverage quadratic interaction terms to model complex feature relationships. We further reveal QNN's ability to expand the feature space and provide smooth nonlinear approximations without relying on activation functions. Meanwhile, we find that traditional post-activation does not further improve the performance of the QNN. Instead, mid-activation is a more suitable alternative. Through theoretical analysis and empirical evaluation of 25 QNN neuron formats, we identify a good-performing variant and make further enhancements on it. Specifically, we propose the Multi-Head Khatri-Rao Product as a superior alternative to HP and a Self-Ensemble Loss with dynamic ensemble capability within the same network to enhance computational efficiency and performance. Ultimately, we propose a novel neuron format, QNN-alpha, which is tailored for CTR prediction tasks. Experimental results show that QNN-alpha achieves new state-of-the-art performance on six public datasets while maintaining low inference latency, good scalability, and excellent compatibility. The code, running logs, and detailed hyperparameter configurations are available at: https://github.com/salmon1802/QNN.

Guoming Li, Jian Yang 0035, Yifan Chen 0004

Filtering-based graph neural networks (GNNs) constitute a distinct class of GNNs that employ graph filters to handle graph-structured data, achieving notable success in various graph-related tasks. Conventional methods adopt a graph-wise filtering paradigm, imposing a uniform filter across all nodes, yet recent findings suggest that this rigid paradigm struggles with heterophilic graphs. To overcome this, recent works have introduced node-wise filtering, which assigns distinct filters to individual nodes, offering enhanced adaptability. However, a fundamental gap remains: a comprehensive framework unifying these two strategies is still absent, limiting theoretical insights into the filtering paradigms. Moreover, through the lens of Contextual Stochastic Block Model, we reveal that a synthesis of graph-wise and node-wise filtering provides a sufficient solution for classification on graphs exhibiting both homophily and heterophily, suggesting the risk of excessive parameterization and potential overfitting with node-wise filtering. To address the limitations, this paper introduces Coarsening-guided Partition-wise Filtering (CPF). CPF innovates by performing filtering on node partitions. The method begins with structure-aware partition-wise filtering, which filters node partitions obtained via graph coarsening algorithms, and then performs feature-aware partition-wise filtering, refining node embeddings via filtering on clusters produced by k-means clustering over features. In-depth analysis is conducted for each phase of CPF, showing its superiority over other paradigms. Finally, benchmark node classification experiments, along with a real-world graph anomaly detection application, validate CPF's efficacy and practical utility. Code is available with the Github repository: https://github.com/vasile-paskardlgm/CPF.

Gaotang Li, Danai Koutra, Yujun Yan

We address the key challenge of size-induced distribution shifts in graph neural networks (GNNs) and their impact on the generalization of GNNs to larger graphs. Existing literature operates under diverse assumptions about distribution shifts, resulting in varying conclusions about the generalizability of GNNs. In contrast to prior work, we adopt a data-driven approach to identify and characterize the types of size-induced distribution shifts and explore their impact on GNN performance from a spectral standpoint, a perspective that has been largely underexplored. Leveraging the significant variance in graph sizes in real biological datasets, we analyze biological graphs and find that spectral differences-driven by subgraph patterns (e.g., average cycle length)-strongly correlate with GNN performance on larger, unseen graphs. Based on these insights, we propose three model-agnostic strategies to enhance GNNs' awareness of critical subgraph patterns, identifying size-intensive attention as the most effective approach. Extensive experiments with six GNN architectures and seven model-agnostic strategies across five datasets show that our size-intensive attention strategy significantly improves graph classification on test graphs 2 to 10 times larger than the training graphs, boosting F1 scores by up to 8% over strong baselines.

Daixun Li, Weiying Xie, Mingxiang Cao, Yunke Wang, Yusi Zhang, Leyuan Fang, Yunsong Li 0001, Chang Xu 0002

Multimodal image fusion and semantic segmentation are critical for autonomous driving. Despite advancements, current models often struggle with segmenting densely packed elements due to a lack of comprehensive fusion features for guidance during training. While the Segment Anything Model (SAM) allows precise control during fine-tuning through its flexible prompting encoder, its potential remains largely unexplored in the context of multimodal segmentation for natural images. In this paper, we introduce SAM into multimodal image segmentation for the first time, proposing a novel framework that combines Latent Space Token Generation (LSTG) and Fusion Mask Prompting (FMP) modules. This approach transforms the training methodology for multimodal segmentation from a traditional black-box approach to a controllable, prompt-based mechanism. Specifically, we obtain latent space features for both modalities through vector quantization and embed them into a cross-attention-based inter-domain fusion module to establish long-range dependencies between modalities. We then use these comprehensive fusion features as prompts to guide precise pixel-level segmentation. Extensive experiments on multiple public datasets demonstrate that our method significantly outperforms SAM and SAM2 in multimodal autonomous driving scenarios, achieving an average improvement of 4.1% over the state-of-the-art method in segmentation mIoU, and the performance is also optimized in other multi-modal visual scenes.

Chenjie Li, Amir Gilad, Boris Glavic, Zhengjie Miao, Sudeepa Roy 0001

Programmatic weak supervision (PWS) significantly reduces human effort for labeling data by combining the outputs of user-provided labeling functions (LFs) on unlabeled datapoints. However, the quality of the generated labels depends directly on the accuracy of the LFs. In this work, we study the problem of fixing LFs based on a small set of labeled examples. Towards this goal, we develop novel techniques for repairing a set of LFs by minimally changing their results on the labeled examples such that the fixed LFs ensure that (i) there is sufficient evidence for the correct label of each labeled datapoint and (ii) the accuracy of each repaired LF is sufficiently high. We model LFs as conditional rules, which enables us to refine them, i.e., to selectively change their output for some inputs. We demonstrate experimentally that our system improves the quality of LFs based on surprisingly small sets of labeled datapoints.

Bingheng Li, Zhikai Chen, Haoyu Han 0001, Shenglai Zeng, Jingzhe Liu, Jiliang Tang

A fundamental challenge in understanding graph neural networks (GNNs) lies in characterizing their optimization dynamics and loss landscape geometry, critical for improving interpretability and robustness. While mode connectivity-a lens for analyzing geometric properties of loss landscapes-has proven insightful for other deep learning architectures, its implications for GNNs remain unexplored. This work presents the first investigation of mode connectivity in GNNs. We uncover that GNNs exhibit distinct non-linear mode connectivity, diverging from patterns observed in fully-connected networks or CNNs. Crucially, we demonstrate that graph structure, rather than model architecture, dominates this behavior, with graph properties like homophily correlating with mode connectivity patterns. We further establish a link between mode connectivity and generalization, proposing a generalization bound based on loss barriers and revealing its utility as a diagnostic tool. Our findings further bridge theoretical insights with practical implications: they rationalize domain alignment strategies in graph learning and provide a foundation for refining GNN training paradigms.

Runze Lei, Pinghui Wang, Juxiang Zeng, Chenxu Wang 0001, Hongbin Pei, Junzhou Zhao

Federated learning (FL) is a popular collaborative training paradigm in which data owners offer gradients instead of private data to model owners for model training to protect data privacy. However, it faces security threats from two sides: dishonest model owners may extract sensitive information about private data from gradients; meanwhile, adversaries may pretend to be data owners and poison the model by sending malicious gradients. We propose a novel FL protocol, PARSIFAL, to address privacy leakage and model poisoning threats. A poisoning detection module is designed based on a novel sketch structure. This module efficiently detects potential malicious gradients that are dissimilar to the majority of benign gradients. PARSIFAL also contains a robust aggregation module based on sign gradients to mitigate the influence of poisoning gradients on aggregation results. Meanwhile, all processes of our PARSIFAL are protected by privacy protocols, mainly based on secret sharing, to guarantee that malicious detection and aggregation processes will not leak sensitive information. Experimental results show that PARSIFAL improves poisoning defense performance by up to 28% compared with recent baselines.