arXiv subjects

Ke Xu

Publications and source records attributed to Ke Xu.

At least 361 records · Page 20Linked to original sources

arXiv2021

Personalized Graph Neural Networks with Attention Mechanism for Session-Aware Recommendation

The problem of session-aware recommendation aims to predict users' next click based on their current session and historical sessions. Existing session-aware recommendation methods have defects in capturing complex item transition relationships. Other than that, most of them fail to explicitly distinguish the effects of different historical sessions on the current session. To this end, we propose a novel method, named Personalized Graph Neural Networks with Attention Mechanism (A-PGNN) for brevity. A-PGNN mainly consists of two components: one is Personalized Graph Neural Network (PGNN), which is used to extract the personalized structural information in each user behavior graph, compared with the traditional Graph Neural Network (GNN) model, which considers the role of the user when the node embeddding is updated. The other is Dot-Product Attention mechanism, which draws on the Transformer net to explicitly model the effect of historical sessions on the current session. Extensive experiments conducted on two real-world data sets show that A-PGNN evidently outperforms the state-of-the-art personalized session-aware recommendation methods.

cs.IR↗

arXiv2020

Synchrotron Microtomography and Neutron Radiography Characterization of the Microstruture and Water Absorption of Concrete from Pompeii

There is renewed interest in using advanced techniques to characterize ancient Roman concrete. In the present work, samples were drilled from the "Hospitium" in Pompeii and were analyzed by synchrotron microtomography (uCT) and neutron radiography to study how the microstructure, including the presence of induced cracks, affects their water adsorption. The water distribution and absorptivity were quantified by neutron radiography. The 3D crack propagation, pore size distribution and orientation, tortuosity, and connectivity were analyzed from uCT results using advanced imaging methods. The concrete characterization also included classical methods (e.g., differential thermal-thermogravimetric, X-ray diffractometry, and scanning electron microscopy). Ductile fracture patterns were observed once cracks were introduced. When compared to Portland cement mortar/concrete, Pompeii samples had relatively high porosity, low connectivity, and similar coefficient of capillary penetration. In addition, the permeability was predicted from models based on percolation theory and the pore structure data to evaluate the fluid transport properties.

physics.app-ph↗

arXiv2020

Robust Attacks on Deep Learning Face Recognition in the Physical World

Deep neural networks (DNNs) have been increasingly used in face recognition (FR) systems. Recent studies, however, show that DNNs are vulnerable to adversarial examples, which can potentially mislead the FR systems using DNNs in the physical world. Existing attacks on these systems either generate perturbations working merely in the digital world, or rely on customized equipments to generate perturbations and are not robust in varying physical environments. In this paper, we propose FaceAdv, a physical-world attack that crafts adversarial stickers to deceive FR systems. It mainly consists of a sticker generator and a transformer, where the former can craft several stickers with different shapes and the latter transformer aims to digitally attach stickers to human faces and provide feedbacks to the generator to improve the effectiveness of stickers. We conduct extensive experiments to evaluate the effectiveness of FaceAdv on attacking 3 typical FR systems (i.e., ArcFace, CosFace and FaceNet). The results show that compared with a state-of-the-art attack, FaceAdv can significantly improve success rate of both dodging and impersonating attacks. We also conduct comprehensive evaluations to demonstrate the robustness of FaceAdv.

cs.CV↗

arXiv2020

Tensile properties of structural I clathrate hydrates:Role of guest-host hydrogen bonding ability

Clathrate hydrates (CHs) are one of the most promising molecular structures in applications of gas capture and storage, and gas separations. Fundamental knowledge of mechanical characteristics of CHs is of crucial importance for assessing gas storage and separations at cold conditions, as well as understanding their stability and formation mechanisms. Here, the tensile mechanical properties of structural I CHs encapsulating a variety of guest species (methane, ammonia, sulfureted hydrogen, formaldehyde, methanol, and methyl mercaptan) that have different abilities to form hydrogen (H-) bonds with water molecule are explored by classical molecular dynamics (MD) simulations. All investigated CHs are structurally stable clathrate structures. Basic mechanical properties of CHs including tensile limit and Young's modulus are dominated by the H-bonding ability of host-guest molecules and the guest molecular polarity. CHs containing small methane, formaldehyde and sulfureted hydrogen guest molecules that possess weak H-bonding ability are mechanically robust clathrate structures and mechanically destabilized via brittle failure on the (1 0 1) plane. However, those entrapping methyl mercaptan, methanol, and ammonia that have strong H-bonding ability are mechanically weak molecular structures and mechanically destabilized through ductile failure as a result of gradual global dissociation of clathrate cages.

physics.comp-ph↗

arXiv2020

Exact Phase Transitions of Model RB with Slower-Growing Domains

The second moment method has always been an effective tool to lower bound the satisfiability threshold of many random constraint satisfaction problems. However, the calculation is usually hard to carry out and as a result, only some loose results can be obtained. In this paper, based on a delicate analysis which fully exploit the power of the second moment method, we prove that random RB instances can exhibit exact phase transition under more relaxed conditions, especially slower-growing domain size. These results are the best by using the second moment method, and new tools should be introduced for any better results.

math.CO↗

arXiv2020

Improving Grammatical Error Correction with Machine Translation Pairs

We propose a novel data synthesis method to generate diverse error-corrected sentence pairs for improving grammatical error correction, which is based on a pair of machine translation models of different qualities (i.e., poor and good). The poor translation model resembles the ESL (English as a second language) learner and tends to generate translations of low quality in terms of fluency and grammatical correctness, while the good translation model generally generates fluent and grammatically correct translations. We build the poor and good translation model with phrase-based statistical machine translation model with decreased language model weight and neural machine translation model respectively. By taking the pair of their translations of the same sentences in a bridge language as error-corrected sentence pairs, we can construct unlimited pseudo parallel data. Our approach is capable of generating diverse fluency-improving patterns without being limited by the pre-defined rule set and the seed error-corrected data. Experimental results demonstrate the effectiveness of our approach and show that it can be combined with other synthetic data sources to yield further improvements.

cs.CL↗

arXiv2020

Pseudo-Bidirectional Decoding for Local Sequence Transduction

Local sequence transduction (LST) tasks are sequence transduction tasks where there exists massive overlapping between the source and target sequences, such as Grammatical Error Correction (GEC) and spell or OCR correction. Previous work generally tackles LST tasks with standard sequence-to-sequence (seq2seq) models that generate output tokens from left to right and suffer from the issue of unbalanced outputs. Motivated by the characteristic of LST tasks, in this paper, we propose a simple but versatile approach named Pseudo-Bidirectional Decoding (PBD) for LST tasks. PBD copies the corresponding representation of source tokens to the decoder as pseudo future context to enable the decoder to attends to its bi-directional context. In addition, the bidirectional decoding scheme and the characteristic of LST tasks motivate us to share the encoder and the decoder of seq2seq models. The proposed PBD approach provides right side context information for the decoder and models the inductive bias of LST tasks, reducing the number of parameters by half and providing good regularization effects. Experimental results on several benchmark datasets show that our approach consistently improves the performance of standard seq2seq models on LST tasks.

cs.CL↗

arXiv2020

Scheduled DropHead: A Regularization Method for Transformer Models

In this paper, we introduce DropHead, a structured dropout method specifically designed for regularizing the multi-head attention mechanism, which is a key component of transformer, a state-of-the-art model for various NLP tasks. In contrast to the conventional dropout mechanisms which randomly drop units or connections, the proposed DropHead is a structured dropout method. It drops entire attention-heads during training and It prevents the multi-head attention model from being dominated by a small portion of attention heads while also reduces the risk of overfitting the training data, thus making use of the multi-head attention mechanism more efficiently. Motivated by recent studies about the learning dynamic of the multi-head attention mechanism, we propose a specific dropout rate schedule to adaptively adjust the dropout rate of DropHead and achieve better regularization effect. Experimental results on both machine translation and text classification benchmark datasets demonstrate the effectiveness of the proposed approach.

cs.CL↗

arXiv2020

BERT Loses Patience: Fast and Robust Inference with Early Exit

In this paper, we propose Patience-based Early Exit, a straightforward yet effective inference method that can be used as a plug-and-play technique to simultaneously improve the efficiency and robustness of a pretrained language model (PLM). To achieve this, our approach couples an internal-classifier with each layer of a PLM and dynamically stops inference when the intermediate predictions of the internal classifiers remain unchanged for a pre-defined number of steps. Our approach improves inference efficiency as it allows the model to make a prediction with fewer layers. Meanwhile, experimental results with an ALBERT model show that our method can improve the accuracy and robustness of the model by preventing it from overthinking and exploiting multiple classifiers for prediction, yielding a better accuracy-speed trade-off compared to existing early exit methods.

cs.CL↗

arXiv2020

Revisiting Image-Language Networks for Open-ended Phrase Detection

Most existing work that grounds natural language phrases in images starts with the assumption that the phrase in question is relevant to the image. In this paper we address a more realistic version of the natural language grounding task where we must both identify whether the phrase is relevant to an image and localize the phrase. This can also be viewed as a generalization of object detection to an open-ended vocabulary, introducing elements of few- and zero-shot detection. We propose an approach for this task that extends Faster R-CNN to relate image regions and phrases. By carefully initializing the classification layers of our network using canonical correlation analysis (CCA), we encourage a solution that is more discerning when reasoning between similar phrases, resulting in over double the performance compared to a naive adaptation on three popular phrase grounding datasets, Flickr30K Entities, ReferIt Game, and Visual Genome, with test-time phrase vocabulary sizes of 5K, 32K, and 159K, respectively.

cs.CV↗

arXiv2020

Weakly-supervised Salient Instance Detection

Existing salient instance detection (SID) methods typically learn from pixel-level annotated datasets. In this paper, we present the first weakly-supervised approach to the SID problem. Although weak supervision has been considered in general saliency detection, it is mainly based on using class labels for object localization. However, it is non-trivial to use only class labels to learn instance-aware saliency information, as salient instances with high semantic affinities may not be easily separated by the labels. We note that subitizing information provides an instant judgement on the number of salient items, which naturally relates to detecting salient instances and may help separate instances of the same class while grouping different parts of the same instance. Inspired by this insight, we propose to use class and subitizing labels as weak supervision for the SID problem. We propose a novel weakly-supervised network with three branches: a Saliency Detection Branch leveraging class consistency information to locate candidate objects; a Boundary Detection Branch exploiting class discrepancy information to delineate object boundaries; and a Centroid Detection Branch using subitizing information to detect salient instance centroids. This complementary information is further fused to produce salient instance maps. We conduct extensive experiments to demonstrate that the proposed method plays favorably against carefully designed baseline methods adapted from related tasks.

cs.CV↗

arXiv2020

Off-Path TCP Exploits of the Mixed IPID Assignment

In this paper, we uncover a new off-path TCP hijacking attack that can be used to terminate victim TCP connections or inject forged data into victim TCP connections by manipulating the new mixed IPID assignment method, which is widely used in Linux kernel version 4.18 and beyond to help defend against TCP hijacking attacks. The attack has three steps. First, an off-path attacker can downgrade the IPID assignment for TCP packets from the more secure per-socket-based policy to the less secure hash-based policy, building a shared IPID counter that forms a side channel on the victim. Second, the attacker detects the presence of TCP connections by observing the shared IPID counter on the victim. Third, the attacker infers the sequence number and the acknowledgment number of the detected connection by observing the side channel of the shared IPID counter. Consequently, the attacker can completely hijack the connection, i.e., resetting the connection or poisoning the data stream. We evaluate the impacts of this off-path TCP attack in the real world. Our case studies of SSH DoS, manipulating web traffic, and poisoning BGP routing tables show its threat on a wide range of applications. Our experimental results show that our off-path TCP attack can be constructed within 215 seconds and the success rate is over 88%. Finally, we analyze the root cause of the exploit and develop a new IPID assignment method to defeat this attack. We prototype our defense in Linux 4.18 and confirm its effectiveness through extensive evaluation over real applications on the Internet.

cs.CR↗

arXiv2020

Mechanical Metastructures of Triple Periodic Carbon Clathrates

Clathrates are lightweight, cage-like, fully-sp3 three dimensional (3D) structures that are experimentally-available for several host elements of the IV group. However, carbon clathrates are as yet hypothetical structures. Herein, the mechanical properties of Type-I-C46 Type-II-C34 and Type-H-C34 carbon clathrates are explored by first-principles calculations. It is revealed that those carbon clathrates show distinct anisotropic patterns in ideal tensile/shear strengths and critical tensile/shear strains, with maximum ideal tensile strength of Type-I carbon clathrate that is superior over that of diamond in <111> direction. However, it is identified isotropy in shear Youngs modulus, and in terms of tensile/shear Youngs moduli, they are sorted as Type-I > Type-II > Type-H carbon clathrates. There are distinct critical load-bearing bond configurations that explain their distinct mechanical behaviors. Moreover, those carbon clathrates are intrinsically indirect semiconductors, and their electronic properties can be greatly dictated by mechanical strain. Carbon clathrates can be potentially utilized as lightweight technically robust engineering metastructures and in electromechanical devices.

cond-mat.mtrl-sci↗

arXiv2020

Oxygen Functionalization-induced Crossover in the Tensile Properties of thinnest 2D Ti2C MXene

Transition metal carbides/nitrides (MXenes) are a newly developing class of two-dimensional (2D) materials with technically robust properties that can be finely tuned by planar surface functionalization. Herein, the critical role of oxygen (O-) functionalization on the tensile mechanical characteristics of thinnest 2D Ti2C MXene is explored by molecular dynamic (MD) simulation with first-principle based ReaxFF forcefield. It is demonstrated that Ti2C sheet shows unique tensile mechanical behaviors that pronouncedly vary with the content of O-functionalization and stretching direction. Upon both loading directions, there is an apparent crossover in the Young's modulus, failure strength and failure strain. Intriguingly, under armchair directional load, a structural transition of 1T to 1T' phase occurs in the Ti2C region, which has been observed in many transition metal dichalcogenides. Upon zigzag directional straining, however, two distinct structural transformations take place in pristine and fully O-functionalized Ti2C sheets, respectively. As the load is removed, those three structural transformations are reversible, and they are critically understood by analysis of the bond configurations. The study provides important insights into mechanical behaviors and structural transformations of functionalized MXenes.

cond-mat.mtrl-sci↗

arXiv2020

Towards Ground Truth Explainability on Tabular Data

In data science, there is a long history of using synthetic data for method development, feature selection and feature engineering. Our current interest in synthetic data comes from recent work in explainability. Today's datasets are typically larger and more complex - requiring less interpretable models. In the setting of \textit{post hoc} explainability, there is no ground truth for explanations. Inspired by recent work in explaining image classifiers that does provide ground truth, we propose a similar solution for tabular data. Using copulas, a concise specification of the desired statistical properties of a dataset, users can build intuition around explainability using controlled data sets and experimentation. The current capabilities are demonstrated on three use cases: one dimensional logistic regression, impact of correlation from informative features, impact of correlation from redundant variables.

cs.LG↗

arXiv2020

Online monitoring for safe pedestrian-vehicle interactions

As autonomous systems begin to operate amongst humans, methods for safe interaction must be investigated. We consider an example of a small autonomous vehicle in a pedestrian zone that must safely maneuver around people in a free-form fashion. We investigate two key questions: How can we effectively integrate pedestrian intent estimation into our autonomous stack. Can we develop an online monitoring framework to give formal guarantees on the safety of such human-robot interactions. We present a pedestrian intent estimation framework that can accurately predict future pedestrian trajectories given multiple possible goal locations. We integrate this into a reachability-based online monitoring scheme that formally assesses the safety of these interactions with nearly real-time performance (approximately 0.3 seconds). These techniques are integrated on a test vehicle with a complete in-house autonomous stack, demonstrating effective and safe interaction in real-world experiments.

cs.RO↗

arXiv2020

Harvesting and Refining Question-Answer Pairs for Unsupervised QA

Question Answering (QA) has shown great success thanks to the availability of large-scale datasets and the effectiveness of neural models. Recent research works have attempted to extend these successes to the settings with few or no labeled data available. In this work, we introduce two approaches to improve unsupervised QA. First, we harvest lexically and syntactically divergent questions from Wikipedia to automatically construct a corpus of question-answer pairs (named as RefQA). Second, we take advantage of the QA model to extract more appropriate answers, which iteratively refines data over RefQA. We conduct experiments on SQuAD 1.1, and NewsQA by fine-tuning BERT without access to manually annotated data. Our approach outperforms previous unsupervised approaches by a large margin and is competitive with early supervised models. We also show the effectiveness of our approach in the few-shot learning setting.

cs.CL↗

arXiv2020

Weak ties strengthen anger contagion in social media

Increasing evidence suggests that, similar to face-to-face communications, human emotions also spread in online social media. However, the mechanisms underlying this emotion contagion, for example, whether different feelings spread in unlikely ways or how the spread of emotions relates to the social network, is rarely investigated. Indeed, because of high costs and spatio-temporal limitations, explorations of this topic are challenging using conventional questionnaires or controlled experiments. Because they are collection points for natural affective responses of massive individuals, online social media sites offer an ideal proxy for tackling this issue from the perspective of computational social science. In this paper, based on the analysis of millions of tweets in Weibo, surprisingly, we find that anger travels easily along weaker ties than joy, meaning that it can infiltrate different communities and break free of local traps because strangers share such content more often. Through a simple diffusion model, we reveal that weaker ties speed up anger by applying both propagation velocity and coverage metrics. To the best of our knowledge, this is the first time that quantitative long-term evidence has been presented that reveals a difference in the mechanism by which joy and anger are disseminated. With the extensive proliferation of weak ties in booming social media, our results imply that the contagion of anger could be profoundly strengthened to globalize its negative impact.

cs.SI↗