Searcharxiv⌕ Search

arXiv subjects

Ke Xu

Publications and source records attributed to Ke Xu.

At least 289 records · Page 16Linked to original sources
arXiv2023

RF-Based Simultaneous Localization and Source Seeking for Multi-Robot Systems

This paper considers a radio-frequency (RF)-based simultaneous localization and source-seeking (SLASS) problem in multi-robot systems, where multiple robots jointly localize themselves and an RF source using distance-only measurements extracted from RF signals and then control themselves to approach the source. We design a Rao-Blackwellized particle filter-based algorithm to realize the joint localization of the robots and the source. We also devise an information-theoretic control policy for the robots to approach the source. In our control policy, we maximize the predicted mutual information between the source position and the distance measurements, conditioned on the robot positions, to incorporate the robot localization uncertainties. A projected gradient ascent method is adopted to solve the mutual information maximization problem. Simulation results show that the proposed SLASS framework outperforms two benchmarks in terms of the root mean square error (RMSE) of the estimated source position and the decline of the distances between the robots and the source, indicating more effective approaching of the robots to the source.

eess.SP↗
arXiv2023

Pulse Shape-Aided Multipath Delay Estimation for Fine-Grained WiFi Sensing

Due to the finite bandwidth of practical wireless systems, one multipath component can manifest itself as a discrete pulse consisting of multiple taps in the digital delay domain. This effect is called channel leakage, which complicates the multipath delay estimation problem. In this paper, we develop a new algorithm to estimate multipath delays of leaked channels by leveraging the knowledge of pulse-shaping functions, which can be used to support fine-grained WiFi sensing applications. Specifically, we express the channel impulse response (CIR) as a linear combination of overcomplete basis vectors corresponding to different delays. Considering the limited number of paths in physical environments, we formulate the multipath delay estimation as a sparse recovery problem. We then propose a sparse Bayesian learning (SBL) method to estimate the sparse vector and determine the number of physical paths and their associated delay parameters from the positions of the nonzero entries in the sparse vector. Simulation results show that our algorithm can accurately determine the number of paths, and achieve superior accuracy in path delay estimation and channel reconstruction compared to two benchmarking schemes.

eess.SP↗
arXiv2023

SEGA: Structural Entropy Guided Anchor View for Graph Contrastive Learning

In contrastive learning, the choice of ``view'' controls the information that the representation captures and influences the performance of the model. However, leading graph contrastive learning methods generally produce views via random corruption or learning, which could lead to the loss of essential information and alteration of semantic information. An anchor view that maintains the essential information of input graphs for contrastive learning has been hardly investigated. In this paper, based on the theory of graph information bottleneck, we deduce the definition of this anchor view; put differently, \textit{the anchor view with essential information of input graph is supposed to have the minimal structural uncertainty}. Furthermore, guided by structural entropy, we implement the anchor view, termed \textbf{SEGA}, for graph contrastive learning. We extensively validate the proposed anchor view on various benchmarks regarding graph classification under unsupervised, semi-supervised, and transfer learning and achieve significant performance boosts compared to the state-of-the-art methods.

cs.LG↗
arXiv2023

HiTIN: Hierarchy-aware Tree Isomorphism Network for Hierarchical Text Classification

Hierarchical text classification (HTC) is a challenging subtask of multi-label classification as the labels form a complex hierarchical structure. Existing dual-encoder methods in HTC achieve weak performance gains with huge memory overheads and their structure encoders heavily rely on domain knowledge. Under such observation, we tend to investigate the feasibility of a memory-friendly model with strong generalization capability that could boost the performance of HTC without prior statistics or label semantics. In this paper, we propose Hierarchy-aware Tree Isomorphism Network (HiTIN) to enhance the text representations with only syntactic information of the label hierarchy. Specifically, we convert the label hierarchy into an unweighted tree structure, termed coding tree, with the guidance of structural entropy. Then we design a structure encoder to incorporate hierarchy-aware information in the coding tree into text representations. Besides the text encoder, HiTIN only contains a few multi-layer perceptions and linear transformations, which greatly saves memory. We conduct experiments on three commonly used datasets and the results demonstrate that HiTIN could achieve better test performance and less memory consumption than state-of-the-art (SOTA) methods.

cs.CL↗
arXiv2023

BandwidthBreach: Unleashing Covert and Side Channels through Cache Bandwidth Exploitation

In the modern CPU architecture, enhancements such as the Line Fill Buffer (LFB) and Super Queue (SQ), which are designed to track pending cache requests, have significantly boosted performance. To exploit this structures, we deliberately engineered blockages in the L2 to L1d route by controlling LFB conflict and triggering prefetch prediction failures, while consciously dismissing other plausible influencing factors. This approach was subsequently extended to the L3 to L2 and L2 to L1i pathways, resulting in three potent covert channels, termed L2CC, L3CC, and LiCC, with capacities of 10.02 Mbps, 10.37 Mbps, and 1.83 Mbps, respectively. Strikingly, the capacities of L2CC and L3CC surpass those of earlier non-shared-memory-based covert channels, reaching a level comparable to their shared memory-dependent equivalents. Leveraging this congestion further facilitated the extraction of key bits from RSA and EdDSA implementations. Coupled with SpectreV1 and V2, our covert channels effectively evade the majority of traditional Spectre defenses. Their confluence with Branch Prediction (BP) Timing assaults additionally undercuts balanced branch protections, hence broadening their capability to infiltrate a wide range of cryptography libraries.

cs.CR↗
arXiv2023

Sub-micrometer phonon mean free paths in metal-organic frameworks revealed by machine-learning molecular dynamics simulations

Metal-organic frameworks (MOFs) are a family of materials that have high porosity and structural tunability and hold great potential in various applications, many of which requiring a proper understanding of the thermal transport properties. Molecular dynamics (MD) simulations play an important role in characterizing the thermal transport properties of various materials. However, due to the complexity of the structures, it is difficult to construct accurate empirical interatomic potentials for reliable MD simulations of MOFs. To this end, we develop a set of accurate yet highly efficient machine-learned potentials for three typical MOFs, including MOF-5, HKUST-1, and ZIF-8, using the neuroevolution potential approach as implemented in the GPUMD package, and perform extensive MD simulations to study thermal transport in the three MOFs. Although the lattice thermal conductivity (LTC) values of the three MOFs are all predicted to be smaller than 1 $\rm{W/(m\ K)}$ at room temperature, the phonon mean free paths (MFPs) are found to reach the sub-micrometer scale in the low-frequency region. As a consequence, the apparent LTC only converges to the diffusive limit for micrometer single crystals, which means that the LTC is heavily reduced in nanocrystalline MOFs. The sub-micrometer phonon MFPs are also found to be correlated with a moderate temperature dependence of LTC between those in typical crystalline and amorphous materials. Both the large phonon MFPs and the moderate temperature dependence of LTC fundamentally change our understanding of thermal transport in MOFs.

cond-mat.mtrl-sci↗
arXiv2023

Mitigating Adversarial Attacks by Distributing Different Copies to Different Users

Machine learning models are vulnerable to adversarial attacks. In this paper, we consider the scenario where a model is distributed to multiple buyers, among which a malicious buyer attempts to attack another buyer. The malicious buyer probes its copy of the model to search for adversarial samples and then presents the found samples to the victim's copy of the model in order to replicate the attack. We point out that by distributing different copies of the model to different buyers, we can mitigate the attack such that adversarial samples found on one copy would not work on another copy. We observed that training a model with different randomness indeed mitigates such replication to a certain degree. However, there is no guarantee and retraining is computationally expensive. A number of works extended the retraining method to enhance the differences among models. However, a very limited number of models can be produced using such methods and the computational cost becomes even higher. Therefore, we propose a flexible parameter rewriting method that directly modifies the model's parameters. This method does not require additional training and is able to generate a large number of copies in a more controllable manner, where each copy induces different adversarial regions. Experimentation studies show that rewriting can significantly mitigate the attacks while retaining high classification accuracy. For instance, on GTSRB dataset with respect to Hop Skip Jump attack, using attractor-based rewriter can reduce the success rate of replicating the attack to 0.5% while independently training copies with different randomness can reduce the success rate to 6.5%. From this study, we believe that there are many further directions worth exploring.

cs.CR↗
arXiv2023

Interactive Natural Language Processing

Interactive Natural Language Processing (iNLP) has emerged as a novel paradigm within the field of NLP, aimed at addressing limitations in existing frameworks while aligning with the ultimate goals of artificial intelligence. This paradigm considers language models as agents capable of observing, acting, and receiving feedback iteratively from external entities. Specifically, language models in this context can: (1) interact with humans for better understanding and addressing user needs, personalizing responses, aligning with human values, and improving the overall user experience; (2) interact with knowledge bases for enriching language representations with factual knowledge, enhancing the contextual relevance of responses, and dynamically leveraging external information to generate more accurate and informed responses; (3) interact with models and tools for effectively decomposing and addressing complex tasks, leveraging specialized expertise for specific subtasks, and fostering the simulation of social behaviors; and (4) interact with environments for learning grounded representations of language, and effectively tackling embodied tasks such as reasoning, planning, and decision-making in response to environmental observations. This paper offers a comprehensive survey of iNLP, starting by proposing a unified definition and framework of the concept. We then provide a systematic classification of iNLP, dissecting its various components, including interactive objects, interaction interfaces, and interaction methods. We proceed to delve into the evaluation methodologies used in the field, explore its diverse applications, scrutinize its ethical and safety issues, and discuss prospective research directions. This survey serves as an entry point for researchers who are interested in this rapidly evolving area and offers a broad view of the current landscape and future trajectory of iNLP.

cs.CL↗
arXiv2023

Rethinking Efficient Lane Detection via Curve Modeling

This paper presents a novel parametric curve-based method for lane detection in RGB images. Unlike state-of-the-art segmentation-based and point detection-based methods that typically require heuristics to either decode predictions or formulate a large sum of anchors, the curve-based methods can learn holistic lane representations naturally. To handle the optimization difficulties of existing polynomial curve methods, we propose to exploit the parametric Bézier curve due to its ease of computation, stability, and high freedom degrees of transformations. In addition, we propose the deformable convolution-based feature flip fusion, for exploiting the symmetry properties of lanes in driving scenes. The proposed method achieves a new state-of-the-art performance on the popular LLAMAS benchmark. It also achieves favorable accuracy on the TuSimple and CULane datasets, while retaining both low latency (> 150 FPS) and small model size (< 10M). Our method can serve as a new baseline, to shed the light on the parametric curves modeling for lane detection. Codes of our model and PytorchAutoDrive: a unified framework for self-driving perception, are available at: https://github.com/voldemortX/pytorch-auto-drive .

cs.CV↗
arXiv2023

Accurate prediction of heat conductivity of water by a neuroevolution potential

We propose an approach that can accurately predict the heat conductivity of liquid water. On the one hand, we develop an accurate machine-learned potential based on the neuroevolution-potential approach that can achieve quantum-mechanical accuracy at the cost of empirical force fields. On the other hand, we combine the Green-Kubo method and the spectral decomposition method within the homogeneous nonequilibrium molecular dynamics framework to account for the quantum-statistical effects of high-frequency vibrations. Excellent agreement with experiments under both isobaric and isochoric conditions within a wide range of temperatures is achieved using our approach.

physics.comp-ph↗
arXiv2023

Multimodal Federated Learning via Contrastive Representation Ensemble

With the increasing amount of multimedia data on modern mobile systems and IoT infrastructures, harnessing these rich multimodal data without breaching user privacy becomes a critical issue. Federated learning (FL) serves as a privacy-conscious alternative to centralized machine learning. However, existing FL methods extended to multimodal data all rely on model aggregation on single modality level, which restrains the server and clients to have identical model architecture for each modality. This limits the global model in terms of both model complexity and data capacity, not to mention task diversity. In this work, we propose Contrastive Representation Ensemble and Aggregation for Multimodal FL (CreamFL), a multimodal federated learning framework that enables training larger server models from clients with heterogeneous model architectures and data modalities, while only communicating knowledge on public dataset. To achieve better multimodal representation fusion, we design a global-local cross-modal ensemble strategy to aggregate client representations. To mitigate local model drift caused by two unprecedented heterogeneous factors stemming from multimodal discrepancy (modality gap and task gap), we further propose two inter-modal and intra-modal contrasts to regularize local training, which complements information of the absent modality for uni-modal clients and regularizes local clients to head towards global consensus. Thorough evaluations and ablation studies on image-text retrieval and visual question answering tasks showcase the superiority of CreamFL over state-of-the-art FL methods and its practical value.

cs.LG↗
arXiv2023

Differentially Private Learning with Per-Sample Adaptive Clipping

Privacy in AI remains a topic that draws attention from researchers and the general public in recent years. As one way to implement privacy-preserving AI, differentially private learning is a framework that enables AI models to use differential privacy (DP). To achieve DP in the learning process, existing algorithms typically limit the magnitude of gradients with a constant clipping, which requires carefully tuned due to its significant impact on model performance. As a solution to this issue, latest works NSGD and Auto-S innovatively propose to use normalization instead of clipping to avoid hyperparameter tuning. However, normalization-based approaches like NSGD and Auto-S rely on a monotonic weight function, which imposes excessive weight on small gradient samples and introduces extra deviation to the update. In this paper, we propose a Differentially Private Per-Sample Adaptive Clipping (DP-PSAC) algorithm based on a non-monotonic adaptive weight function, which guarantees privacy without the typical hyperparameter tuning process of using a constant clipping while significantly reducing the deviation between the update and true batch-averaged gradient. We provide a rigorous theoretical convergence analysis and show that with convergence rate at the same order, the proposed algorithm achieves a lower non-vanishing bound, which is maintained over training iterations, compared with NSGD/Auto-S. In addition, through extensive experimental evaluation, we show that DP-PSAC outperforms or matches the state-of-the-art methods on multiple main-stream vision and language tasks.

cs.LG↗
arXiv2023

Detecting Political Opinions in Tweets through Bipartite Graph Analysis: A Skip Aggregation Graph Convolution Approach

Public opinion is a crucial factor in shaping political decision-making. Nowadays, social media has become an essential platform for individuals to engage in political discussions and express their political views, presenting researchers with an invaluable resource for analyzing public opinion. In this paper, we focus on the 2020 US presidential election and create a large-scale dataset from Twitter. To detect political opinions in tweets, we build a user-tweet bipartite graph based on users' posting and retweeting behaviors and convert the task into a Graph Neural Network (GNN)-based node classification problem. Then, we introduce a novel skip aggregation mechanism that makes tweet nodes aggregate information from second-order neighbors, which are also tweet nodes due to the graph's bipartite nature, effectively leveraging user behavioral information. The experimental results show that our proposed model significantly outperforms several competitive baselines. Further analyses demonstrate the significance of user behavioral information and the effectiveness of skip aggregation.

cs.SI↗
arXiv2023

Graph Collaborative Signals Denoising and Augmentation for Recommendation

Graph collaborative filtering (GCF) is a popular technique for capturing high-order collaborative signals in recommendation systems. However, GCF's bipartite adjacency matrix, which defines the neighbors being aggregated based on user-item interactions, can be noisy for users/items with abundant interactions and insufficient for users/items with scarce interactions. Additionally, the adjacency matrix ignores user-user and item-item correlations, which can limit the scope of beneficial neighbors being aggregated. In this work, we propose a new graph adjacency matrix that incorporates user-user and item-item correlations, as well as a properly designed user-item interaction matrix that balances the number of interactions across all users. To achieve this, we pre-train a graph-based recommendation method to obtain users/items embeddings, and then enhance the user-item interaction matrix via top-K sampling. We also augment the symmetric user-user and item-item correlation components to the adjacency matrix. Our experiments demonstrate that the enhanced user-item interaction matrix with improved neighbors and lower density leads to significant benefits in graph-based recommendation. Moreover, we show that the inclusion of user-user and item-item correlations can improve recommendations for users with both abundant and insufficient interactions. The code is in \url{https://github.com/zfan20/GraphDA}.

cs.IR↗
arXiv2023

Deploying Offline Reinforcement Learning with Human Feedback

Reinforcement learning (RL) has shown promise for decision-making tasks in real-world applications. One practical framework involves training parameterized policy models from an offline dataset and subsequently deploying them in an online environment. However, this approach can be risky since the offline training may not be perfect, leading to poor performance of the RL models that may take dangerous actions. To address this issue, we propose an alternative framework that involves a human supervising the RL models and providing additional feedback in the online deployment phase. We formalize this online deployment problem and develop two approaches. The first approach uses model selection and the upper confidence bound algorithm to adaptively select a model to deploy from a candidate set of trained offline RL models. The second approach involves fine-tuning the model in the online deployment phase when a supervision signal arrives. We demonstrate the effectiveness of these approaches for robot locomotion control and traffic light control tasks through empirical validation.

cs.LG↗
arXiv2023

MAKE: Vision-Language Pre-training based Product Retrieval in Taobao Search

Taobao Search consists of two phases: the retrieval phase and the ranking phase. Given a user query, the retrieval phase returns a subset of candidate products for the following ranking phase. Recently, the paradigm of pre-training and fine-tuning has shown its potential in incorporating visual clues into retrieval tasks. In this paper, we focus on solving the problem of text-to-multimodal retrieval in Taobao Search. We consider that users' attention on titles or images varies on products. Hence, we propose a novel Modal Adaptation module for cross-modal fusion, which helps assigns appropriate weights on texts and images across products. Furthermore, in e-commerce search, user queries tend to be brief and thus lead to significant semantic imbalance between user queries and product titles. Therefore, we design a separate text encoder and a Keyword Enhancement mechanism to enrich the query representations and improve text-to-multimodal matching. To this end, we present a novel vision-language (V+L) pre-training methods to exploit the multimodal information of (user query, product title, product image). Extensive experiments demonstrate that our retrieval-specific pre-training model (referred to as MAKE) outperforms existing V+L pre-training methods on the text-to-multimodal retrieval task. MAKE has been deployed online and brings major improvements on the retrieval system of Taobao Search.

cs.IR↗
arXiv2023

Orthogonal-Time-Frequency-Space Signal Design for Integrated Data and Energy Transfer: Benefits from Doppler Offsets

Integrated data and energy transfer (IDET) is an advanced technology for enabling energy sustainability for massively deployed low-power electronic consumption components. However, the existing work of IDET using the orthogonal-frequency-division-multiplexing (OFDM) waveforms is designed for static scenarios, which would be severely affected by the destructive Doppler offset in high-mobility scenarios. Therefore, we proposed an IDET system based on orthogonal-time-frequency-space (OTFS) waveforms with the imperfect channel assumption, which is capable of counteracting the Doppler offset in high-mobility scenarios. At the transmitter, the OTFS-IDET system superimposes the random data signals and deterministic energy signals in the delay-Doppler (DD) domain with optimally designed amplitudes. The receiver optimally splits the received signal in the power domain for achieving the best IDET performance. After formulating a non-convex optimisation problem, it is transformed into a geometric programming (GP) problem through inequality relaxations to obtain the optimal solution. The simulation demonstrates that a higher amount of energy can be harvested when employing our proposed OTFS-IDET waveforms than the conventional OFDM-IDET ones in high mobility scenarios.

eess.SP↗
arXiv2023

Detecting Unknown Encrypted Malicious Traffic in Real Time via Flow Interaction Graph Analysis

In this paper, we propose HyperVision, a realtime unsupervised machine learning (ML) based malicious traffic detection system. Particularly, HyperVision is able to detect unknown patterns of encrypted malicious traffic by utilizing a compact inmemory graph built upon the traffic patterns. The graph captures flow interaction patterns represented by the graph structural features, instead of the features of specific known attacks. We develop an unsupervised graph learning method to detect abnormal interaction patterns by analyzing the connectivity, sparsity, and statistical features of the graph, which allows HyperVision to detect various encrypted attack traffic without requiring any labeled datasets of known attacks. Moreover, we establish an information theory model to demonstrate that the information preserved by the graph approaches the ideal theoretical bound. We show the performance of HyperVision by real-world experiments with 92 datasets including 48 attacks with encrypted malicious traffic. The experimental results illustrate that HyperVision achieves at least 0.92 AUC and 0.86 F1, which significantly outperform the state-of-the-art methods. In particular, more than 50% attacks in our experiments can evade all these methods. Moreover, HyperVision achieves at least 80.6 Gb/s detection throughput with the average detection latency of 0.83s.

cs.CR↗