arXiv subjects

Meng Han

Publications and source records attributed to Meng Han.

At least 91 records · Page 5Linked to original sources

arXiv2024

E-SAGE: Explainability-based Defense Against Backdoor Attacks on Graph Neural Networks

Graph Neural Networks (GNNs) have recently been widely adopted in multiple domains. Yet, they are notably vulnerable to adversarial and backdoor attacks. In particular, backdoor attacks based on subgraph insertion have been shown to be effective in graph classification tasks while being stealthy, successfully circumventing various existing defense methods. In this paper, we propose E-SAGE, a novel approach to defending GNN backdoor attacks based on explainability. We find that the malicious edges and benign edges have significant differences in the importance scores for explainability evaluation. Accordingly, E-SAGE adaptively applies an iterative edge pruning process on the graph based on the edge scores. Through extensive experiments, we demonstrate the effectiveness of E-SAGE against state-of-the-art graph backdoor attacks in different attack settings. In addition, we investigate the effectiveness of E-SAGE against adversarial attacks.

cs.CR↗

arXiv2024

ReDas: A Lightweight Architecture for Supporting Fine-Grained Reshaping and Multiple Dataflows on Systolic Array

The systolic accelerator is one of the premier architectural choices for DNN acceleration. However, the conventional systolic architecture suffers from low PE utilization due to the mismatch between the fixed array and diverse DNN workloads. Recent studies have proposed flexible systolic array architectures to adapt to DNN models. However, these designs support only coarse-grained reshaping or significantly increase hardware overhead. In this study, we propose ReDas, a flexible and lightweight systolic array that supports dynamic fine-grained reshaping and multiple dataflows. First, ReDas integrates lightweight and reconfigurable roundabout data paths, which achieve fine-grained reshaping using only short connections between adjacent PEs. Second, we redesign the PE microarchitecture and integrate a set of multi-mode data buffers around the array. The PE structure enables additional data bypassing and flexible data switching. Simultaneously, the multi-mode buffers facilitate fine-grained reallocation of on-chip memory resources, adapting to various dataflow requirements. ReDas can dynamically reconfigure to up to 129 different logical shapes and 3 dataflows for a 128x128 array. Finally, we propose an efficient mapper to generate appropriate configurations for each layer of DNN workloads. Compared to the conventional systolic array, ReDas can achieve about 4.6x speedup and 8.3x energy-delay product (EDP) reduction.

cs.AR↗

arXiv2024

A Survey of Privacy Threats and Defense in Vertical Federated Learning: From Model Life Cycle Perspective

Vertical Federated Learning (VFL) is a federated learning paradigm where multiple participants, who share the same set of samples but hold different features, jointly train machine learning models. Although VFL enables collaborative machine learning without sharing raw data, it is still susceptible to various privacy threats. In this paper, we conduct the first comprehensive survey of the state-of-the-art in privacy attacks and defenses in VFL. We provide taxonomies for both attacks and defenses, based on their characterizations, and discuss open challenges and future research directions. Specifically, our discussion is structured around the model's life cycle, by delving into the privacy threats encountered during different stages of machine learning and their corresponding countermeasures. This survey not only serves as a resource for the research community but also offers clear guidance and actionable insights for practitioners to safeguard data privacy throughout the model's life cycle.

cs.CR↗

arXiv2023

Argue with Me Tersely: Towards Sentence-Level Counter-Argument Generation

Counter-argument generation -- a captivating area in computational linguistics -- seeks to craft statements that offer opposing views. While most research has ventured into paragraph-level generation, sentence-level counter-argument generation beckons with its unique constraints and brevity-focused challenges. Furthermore, the diverse nature of counter-arguments poses challenges for evaluating model performance solely based on n-gram-based metrics. In this paper, we present the ArgTersely benchmark for sentence-level counter-argument generation, drawing from a manually annotated dataset from the ChangeMyView debate forum. We also propose Arg-LlaMA for generating high-quality counter-argument. For better evaluation, we trained a BERT-based evaluator Arg-Judge with human preference data. We conducted comparative experiments involving various baselines such as LlaMA, Alpaca, GPT-3, and others. The results show the competitiveness of our proposed framework and evaluator in counter-argument generation tasks. Code and data are available at https://github.com/amazingljy1206/ArgTersely.

cs.CL↗

arXiv2023

Hi-ArG: Exploring the Integration of Hierarchical Argumentation Graphs in Language Pretraining

The knowledge graph is a structure to store and represent knowledge, and recent studies have discussed its capability to assist language models for various applications. Some variations of knowledge graphs aim to record arguments and their relations for computational argumentation tasks. However, many must simplify semantic types to fit specific schemas, thus losing flexibility and expression ability. In this paper, we propose the Hierarchical Argumentation Graph (Hi-ArG), a new structure to organize arguments. We also introduce two approaches to exploit Hi-ArG, including a text-graph multi-modal model GreaseArG and a new pre-training framework augmented with graph information. Experiments on two argumentation tasks have shown that after further pre-training and fine-tuning, GreaseArG supersedes same-scale language models on these tasks, while incorporating graph information during further pre-training can also improve the performance of vanilla language models. Code for this paper is available at https://github.com/ljcleo/Hi-ArG .

cs.CL↗

arXiv2023

IAG: Induction-Augmented Generation Framework for Answering Reasoning Questions

Retrieval-Augmented Generation (RAG), by incorporating external knowledge with parametric memory of language models, has become the state-of-the-art architecture for open-domain QA tasks. However, common knowledge bases are inherently constrained by limited coverage and noisy information, making retrieval-based approaches inadequate to answer implicit reasoning questions. In this paper, we propose an Induction-Augmented Generation (IAG) framework that utilizes inductive knowledge along with the retrieved documents for implicit reasoning. We leverage large language models (LLMs) for deriving such knowledge via a novel prompting method based on inductive reasoning patterns. On top of this, we implement two versions of IAG named IAG-GPT and IAG-Student, respectively. IAG-GPT directly utilizes the knowledge generated by GPT-3 for answer prediction, while IAG-Student gets rid of dependencies on GPT service at inference time by incorporating a student inductor model. The inductor is firstly trained via knowledge distillation and further optimized by back-propagating the generator feedback via differentiable beam scores. Experimental results show that IAG outperforms RAG baselines as well as ChatGPT on two Open-Domain QA tasks. Notably, our best models have won the first place in the official leaderboards of CSQA2.0 (since Nov 1, 2022) and StrategyQA (since Jan 8, 2023).

cs.CL↗

arXiv2023

Scribble-based 3D Multiple Abdominal Organ Segmentation via Triple-branch Multi-dilated Network with Pixel- and Class-wise Consistency

Multi-organ segmentation in abdominal Computed Tomography (CT) images is of great importance for diagnosis of abdominal lesions and subsequent treatment planning. Though deep learning based methods have attained high performance, they rely heavily on large-scale pixel-level annotations that are time-consuming and labor-intensive to obtain. Due to its low dependency on annotation, weakly supervised segmentation has attracted great attention. However, there is still a large performance gap between current weakly-supervised methods and fully supervised learning, leaving room for exploration. In this work, we propose a novel 3D framework with two consistency constraints for scribble-supervised multiple abdominal organ segmentation from CT. Specifically, we employ a Triple-branch multi-Dilated network (TDNet) with one encoder and three decoders using different dilation rates to capture features from different receptive fields that are complementary to each other to generate high-quality soft pseudo labels. For more stable unsupervised learning, we use voxel-wise uncertainty to rectify the soft pseudo labels and then supervise the outputs of each decoder. To further regularize the network, class relationship information is exploited by encouraging the generated class affinity matrices to be consistent across different decoders under multi-view projection. Experiments on the public WORD dataset show that our method outperforms five existing scribble-supervised methods.

cs.CV↗

arXiv2023

Dual-view Curricular Optimal Transport for Cross-lingual Cross-modal Retrieval

Current research on cross-modal retrieval is mostly English-oriented, as the availability of a large number of English-oriented human-labeled vision-language corpora. In order to break the limit of non-English labeled data, cross-lingual cross-modal retrieval (CCR) has attracted increasing attention. Most CCR methods construct pseudo-parallel vision-language corpora via Machine Translation (MT) to achieve cross-lingual transfer. However, the translated sentences from MT are generally imperfect in describing the corresponding visual contents. Improperly assuming the pseudo-parallel data are correctly correlated will make the networks overfit to the noisy correspondence. Therefore, we propose Dual-view Curricular Optimal Transport (DCOT) to learn with noisy correspondence in CCR. In particular, we quantify the confidence of the sample pair correlation with optimal transport theory from both the cross-lingual and cross-modal views, and design dual-view curriculum learning to dynamically model the transportation costs according to the learning stage of the two views. Extensive experiments are conducted on two multilingual image-text datasets and one video-text dataset, and the results demonstrate the effectiveness and robustness of the proposed method. Besides, our proposed method also shows a good expansibility to cross-lingual image-text baselines and a decent generalization on out-of-domain data.

cs.CV↗

arXiv2023

FuseFPS: Accelerating Farthest Point Sampling with Fusing KD-tree Construction for Point Clouds

Point cloud analytics has become a critical workload for embedded and mobile platforms across various applications. Farthest point sampling (FPS) is a fundamental and widely used kernel in point cloud processing. However, the heavy external memory access makes FPS a performance bottleneck for real-time point cloud processing. Although bucket-based farthest point sampling can significantly reduce unnecessary memory accesses during the point sampling stage, the KD-tree construction stage becomes the predominant contributor to execution time. In this paper, we present FuseFPS, an architecture and algorithm co-design for bucket-based farthest point sampling. We first propose a hardware-friendly sampling-driven KD-tree construction algorithm. The algorithm fuses the KD-tree construction stage into the point sampling stage, further reducing memory accesses. Then, we design an efficient accelerator for bucket-based point sampling. The accelerator can offload the entire bucket-based FPS kernel at a low hardware cost. Finally, we evaluate our approach on various point cloud datasets. The detailed experiments show that compared to the state-of-the-art accelerator QuickFPS, FuseFPS achieves about 4.3$\times$ and about 6.1$\times$ improvements on speed and power efficiency, respectively.

cs.AR↗

arXiv2023

Deep Reinforcement Learning-driven Cross-Community Energy Interaction Optimal Scheduling

In order to coordinate energy interactions among various communities and energy conversions among multi-energy subsystems within the multi-community integrated energy system under uncertain conditions, and achieve overall optimization and scheduling of the comprehensive energy system, this paper proposes a comprehensive scheduling model that utilizes a multi-agent deep reinforcement learning algorithm to learn load characteristics of different communities and make decisions based on this knowledge. In this model, the scheduling problem of the integrated energy system is transformed into a Markov decision process and solved using a data-driven deep reinforcement learning algorithm, which avoids the need for modeling complex energy coupling relationships between multi-communities and multi-energy subsystems. The simulation results show that the proposed method effectively captures the load characteristics of different communities and utilizes their complementary features to coordinate reasonable energy interactions among them. This leads to a reduction in wind curtailment rate from 16.3% to 0% and lowers the overall operating cost by 5445.6 Yuan, demonstrating significant economic and environmental benefits.

eess.SY↗

arXiv2023

Uncovering Promises and Challenges of Federated Learning to Detect Cardiovascular Diseases: A Scoping Literature Review

Cardiovascular diseases (CVD) are the leading cause of death globally, and early detection can significantly improve outcomes for patients. Machine learning (ML) models can help diagnose CVDs early, but their performance is limited by the data available for model training. Privacy concerns in healthcare make it harder to acquire data to train accurate ML models. Federated learning (FL) is an emerging approach to machine learning that allows models to be trained on data from multiple sources without compromising the privacy of the individual data owners. This survey paper provides an overview of the current state-of-the-art in FL for CVD detection. We review the different FL models proposed in various papers and discuss their advantages and challenges. We also compare FL with traditional centralized learning approaches and highlight the differences in terms of model accuracy, privacy, and data distribution handling capacity. Finally, we provide a critical analysis of FL's current challenges and limitations for CVD detection and discuss potential avenues for future research. Overall, this survey paper aims to provide a comprehensive overview of the current state-of-the-art in FL for CVD detection and to highlight its potential for improving the accuracy and privacy of CVD detection models.

cs.LG↗

arXiv2023

Partial wave effects in the heavy quarkonium radiative electromagnetic decays

In a previous paper \cite{Bc}, it was pointed out that the wave functions of all particles are not pure waves, besides the main partial waves, they all contain {other partial waves}. It is very interesting to know what role these different partial waves play in particle transitions. Therefore, by using the Bethe-Salpeter equation method, we study the radiative electromagnetic decays $ψ\rightarrowγχ_{_{cJ}}$ and $Υ\rightarrowγχ_{_{bJ}}$ ($J=0,1,2$). We find that for the $S$ and $P$ wave dominated states, like the $ψ(2S)$, $Υ(2S)$, $χ_{_{cJ}}(1P)$, and $χ_{_{bJ}}(1P)$ etc., the dominant $S$ and $P$ waves provide main and nonrelativistic contrition to the decays; other partial waves mainly contribute to the relativistic correction. For the states like the $ψ(1D)$, $Υ(2D)$, $χ_{c2}(1F)$, and $χ_{b2}(1F)$ etc., they are the $S-P-D$ mixing state dominated by $D$ wave or the $P-D-F$ mixing state dominated by $F$ wave. Large decay widths are found in the transitions $ψ(2D)\to χ_{c2}(1F)$, $Υ(1D)\to χ_{bJ}(1P)$, and $Υ(2D)\to χ_{bJ}(2P)$ etc., which may be helpful to study the missing states $χ_{c2}(1F)$, $Υ(1D)$, and $Υ(2D)$.

hep-ph↗

arXiv2023

Photoelectronic mapping of spin-orbit interaction of intense light fields

The interaction between a quantum particle's spin angular momentum and its orbital angular momentum is ubiquitous in nature. In optics, the spin-orbit optical phenomenon is closely related with the light-matter interaction and has been of great interest. With the development of laser technology, the high-power and ultrafast light sources now serve as a crucial tool in revealing the behaviour of matters under extreme conditions. The comprehensive knowledge of the spin-orbit interaction for the intense light is of utmost importance. Here, we achieve the in-situ modulation and visualization of the optical orbital-to-spin conversion in strong-field regime. We show that, through manipulating the morphology of femtosecond cylindrical vector vortex pulses by a slit, the photons' orbital angular momentum can be controllably transformed into spin after focusing. By employing strong-field ionization experiment, the orbital-to-spin conversion can be imaged and measured through the photoelectron momentum distributions. Such detection and consequent control of spin-orbit dynamics of intense laser fields have implications on controlling the photoelectron holography and coherent extreme ultraviolet radiation.

physics.optics↗

arXiv2023

Decay properties of $D_{s0}^*(2317)^+$ as a conventional $c\bar s$ meson

Taking $D_{s0}^{*}(2317)^{+ }$ as a conventional $c\bar s$ meson, we calculate its dominant strong and electromagnetic decays in the framework of the Bethe-Salpeter method. Our results are $Γ(D_{s0}^{*+}\to D_s^+π^0) = 7.83^{+1.97}_{-1.55}$ keV and $Γ(D_{s0}^{*+}\to D_s^{*+}γ) = 2.55^{+0.37}_{-0.45}$ keV. The contributions of the different partial waves from the initial and final state wave functions to the decay width are also calculated, and we find that the relativistic corrections in both decay processes are very large.

hep-ph↗

arXiv2023

Query Structure Modeling for Inductive Logical Reasoning Over Knowledge Graphs

Logical reasoning over incomplete knowledge graphs to answer complex logical queries is a challenging task. With the emergence of new entities and relations in constantly evolving KGs, inductive logical reasoning over KGs has become a crucial problem. However, previous PLMs-based methods struggle to model the logical structures of complex queries, which limits their ability to generalize within the same structure. In this paper, we propose a structure-modeled textual encoding framework for inductive logical reasoning over KGs. It encodes linearized query structures and entities using pre-trained language models to find answers. For structure modeling of complex queries, we design stepwise instructions that implicitly prompt PLMs on the execution order of geometric operations in each query. We further separately model different geometric operations (i.e., projection, intersection, and union) on the representation space using a pre-trained encoder with additional attention and maxout layers to enhance structured modeling. We conduct experiments on two inductive logical reasoning datasets and three transductive datasets. The results demonstrate the effectiveness of our method on logical reasoning over KGs in both inductive and transductive settings.

cs.CL↗

arXiv2023

Privacy-Enhancing Technologies in Federated Learning for the Internet of Healthcare Things: A Survey

Advancements in wearable medical devices in IoT technology are shaping the modern healthcare system. With the emergence of the Internet of Healthcare Things (IoHT), we are witnessing how efficient healthcare services are provided to patients and how healthcare professionals are effectively used AI-based models to analyze the data collected from IoHT devices for the treatment of various diseases. To avoid privacy breaches, these data must be processed and analyzed in compliance with the legal rules and regulations such as HIPAA and GDPR. Federated learning is a machine leaning based approach that allows multiple entities to collaboratively train a ML model without sharing their data. This is particularly useful in the healthcare domain where data privacy and security are big concerns. Even though FL addresses some privacy concerns, there is still no formal proof of privacy guarantees for IoHT data. Privacy Enhancing Technologies (PETs) are a set of tools and techniques that are designed to enhance the privacy and security of online communications and data sharing. PETs provide a range of features that help protect users' personal information and sensitive data from unauthorized access and tracking. This paper reviews PETs in detail and comprehensively in relation to FL in the IoHT setting and identifies several key challenges for future research.

cs.NI↗

arXiv2023

Observation of Nuclear-wavepacket Interference in Ultrafast Inter-atomic Energy Transfer

We report the experimental observation of quantum interference in the nuclear wave-packet dynamics driving ultrafast excitation-energy transfer in argon dimers below the threshold of interatomic Coulombic decay (ICD). Using time-resolved photoion-photoion coincidence spectroscopy and quantum dynamics simulations, we reveal that the electronic relaxation dynamics of the inner-valence $3s$ hole on one atom leading to a $4s$ or $4p$ excitation on the other one is influenced by nuclear quantum dynamics in the initial state, giving rise to a deep, periodic modulation on the kinetic-energy-release (KER) spectra of the coincident Ar$^+$-Ar$^+$ ion pairs. Moreover, the time-resolved KER spectra show characteristic fingerprints of quantum interference effects during the energy-transfer process. Our findings pave the way to elucidating quantum-interference effects in ultrafast charge- and energy-transfer dynamics in more complex systems.

physics.atm-clus↗

arXiv2023

ATA-Cache: Contention Mitigation for GPU Shared L1 Cache with Aggregated Tag Array

GPU shared L1 cache is a promising architecture while still suffering from high resource contentions. We present a GPU shared L1 cache architecture with an aggregated tag array that minimizes the L1 cache contentions and takes full advantage of inter-core locality. The key idea is to decouple and aggregate the tag arrays of multiple L1 caches so that the cache requests can be compared with all tag arrays in parallel to probe the replicated data in other caches. The GPU caches are only accessed by other GPU cores when replicated data exists, filtering out unnecessary cache accesses that cause high resource contentions. The experimental results show that GPU IPC can be improved by 12% on average for applications with a high inter-core locality.

cs.AR↗