arXiv subjects

Yi Han

Publications and source records attributed to Yi Han.

90 records · Page 5Linked to original sources

arXiv2022

Learning to Rank Rationales for Explainable Recommendation

State-of-the-art recommender system (RS) mostly rely on complex deep neural network (DNN) model structure, which makes it difficult to provide explanations along with RS decisions. Previous researchers have proved that providing explanations along with recommended items can help users make informed decisions and improve their trust towards the uninterpretable blackbox system. In model-agnostic explainable recommendation, system designers deploy a separate explanation model to take as input from the decision model, and generate explanations to meet the goal of persuasiveness. In this work, we explore the task of ranking textual rationales (supporting evidences) for model-agnostic explainable recommendation. Most of existing rationales ranking algorithms only utilize the rationale IDs and interaction matrices to build latent factor representations; and the semantic information within the textual rationales are not learned effectively. We argue that such design is suboptimal as the important semantic information within the textual rationales may be used to better profile user preferences and item features. Seeing this gap, we propose a model named Semantic-Enhanced Bayesian Personalized Explanation Ranking (SE-BPER) to effectively combine the interaction information and semantic information. SE-BPER first initializes the latent factor representations with contextualized embeddings generated by transformer model, then optimizes them with the interaction data. Extensive experiments show that such methodology improves the rationales ranking performance while simplifying the model training process (fewer hyperparameters and faster convergence). We conclude that the optimal way to combine semantic and interaction information remains an open question in the task of rationales ranking.

cs.IR↗

arXiv2021

Research on facial expression recognition based on Multimodal data fusion and neural network

Facial expression recognition is a challenging task when neural network is applied to pattern recognition. Most of the current recognition research is based on single source facial data, which generally has the disadvantages of low accuracy and low robustness. In this paper, a neural network algorithm of facial expression recognition based on multimodal data fusion is proposed. The algorithm is based on the multimodal data, and it takes the facial image, the histogram of oriented gradient of the image and the facial landmarks as the input, and establishes CNN, LNN and HNN three sub neural networks to extract data features, using multimodal data feature fusion mechanism to improve the accuracy of facial expression recognition. Experimental results show that, benefiting by the complementarity of multimodal data, the algorithm has a great improvement in accuracy, robustness and detection speed compared with the traditional facial expression recognition algorithm. Especially in the case of partial occlusion, illumination and head posture transformation, the algorithm also shows a high confidence.

cs.CV↗

arXiv2021

Knowledge Enhanced Multi-modal Fake News Detection

Recent years have witnessed the significant damage caused by various types of fake news. Although considerable effort has been applied to address this issue and much progress has been made on detecting fake news, most existing approaches mainly rely on the textual content and/or social context, while knowledge-level information---entities extracted from the news content and the relations between them---is much less explored. Within the limited work on knowledge-based fake news detection, an external knowledge graph is often required, which may introduce additional problems: it is quite common for entities and relations, especially with respect to new concepts, to be missing in existing knowledge graphs, and both entity prediction and link prediction are open research questions themselves. Therefore, in this work, we investigate \textbf{knowledge-based fake news detection that does not require any external knowledge graph.} Specifically, our contributions include: (1) transforming the problem of detecting fake news into a subgraph classification task---entities and relations are extracted from each news item to form a single knowledge graph, where a news item is represented by a subgraph. Then a graph neural network (GNN) model is trained to classify each subgraph/news item. (2) Further improving the performance of this model through a simple but effective multi-modal technique that combines extracted knowledge, textual content and social context. Experiments on multiple datasets with thousands of labelled news items demonstrate that our knowledge-based algorithm outperforms existing counterpart methods, and its performance can be further boosted by the multi-modal approach.

cs.SI↗

arXiv2021

Deep Reinforcement Learning for Combinatorial Optimization: Covering Salesman Problems

This paper introduces a new deep learning approach to approximately solve the Covering Salesman Problem (CSP). In this approach, given the city locations of a CSP as input, a deep neural network model is designed to directly output the solution. It is trained using the deep reinforcement learning without supervision. Specifically, in the model, we apply the Multi-head Attention to capture the structural patterns, and design a dynamic embedding to handle the dynamic patterns of the problem. Once the model is trained, it can generalize to various types of CSP tasks (different sizes and topologies) with no need of re-training. Through controlled experiments, the proposed approach shows desirable time complexity: it runs more than 20 times faster than the traditional heuristic solvers with a tiny gap of optimality. Moreover, it significantly outperforms the current state-of-the-art deep learning approaches for combinatorial optimization in the aspect of both training and inference. In comparison with traditional solvers, this approach is highly desirable for most of the challenging tasks in practice that are usually large-scale and require quick decisions.

cs.NE↗

arXiv2021

Example-based Real-time Clothing Synthesis for Virtual Agents

We present a real-time cloth animation method for dressing virtual humans of various shapes and poses. Our approach formulates the clothing deformation as a high-dimensional function of body shape parameters and pose parameters. In order to accelerate the computation, our formulation factorizes the clothing deformation into two independent components: the deformation introduced by body pose variation (Clothing Pose Model) and the deformation from body shape variation (Clothing Shape Model). Furthermore, we sample and cluster the poses spanning the entire pose space and use those clusters to efficiently calculate the anchoring points. We also introduce a sensitivity-based distance measurement to both find nearby anchoring points and evaluate their contributions to the final animation. Given a query shape and pose of the virtual agent, we synthesize the resulting clothing deformation by blending the Taylor expansion results of nearby anchoring points. Compared to previous methods, our approach is general and able to add the shape dimension to any clothing pose model. %and therefore it is more general. Furthermore, we can animate clothing represented with tens of thousands of vertices at 50+ FPS on a CPU. Moreover, our example database is more representative and can be generated in parallel, and thereby saves the training time. We also conduct a user evaluation and show that our method can improve a user's perception of dressed virtual agents in an immersive virtual environment compared to a conventional linear blend skinning method.

cs.GR↗

arXiv2020

Breaking the Memory Wall for AI Chip with a New Dimension

Recent advancements in deep learning have led to the widespread adoption of artificial intelligence (AI) in applications such as computer vision and natural language processing. As neural networks become deeper and larger, AI modeling demands outstrip the capabilities of conventional chip architectures. Memory bandwidth falls behind processing power. Energy consumption comes to dominate the total cost of ownership. Currently, memory capacity is insufficient to support the most advanced NLP models. In this work, we present a 3D AI chip, called Sunrise, with near-memory computing architecture to address these three challenges. This distributed, near-memory computing architecture allows us to tear down the performance-limiting memory wall with an abundance of data bandwidth. We achieve the same level of energy efficiency on 40nm technology as competing chips on 7nm technology. By moving to similar technologies as other AI chips, we project to achieve more than ten times the energy efficiency, seven times the performance of the current state-of-the-art chips, and twenty times of memory capacity as compared with the best chip in each benchmark.

cs.AR↗

arXiv2020

E-commerce Recommendation with Weighted Expected Utility

Different from shopping at retail stores, consumers on e-commerce platforms usually cannot touch or try products before purchasing, which means that they have to make decisions when they are uncertain about the outcome (e.g., satisfaction level) of purchasing a product. To study people's preferences, economics researchers have proposed the hypothesis of Expected Utility (EU) that models the subject value associated with an individual's choice as the statistical expectations of that individual's valuations of the outcomes of this choice. Despite its success in studies of game theory and decision theory, the effectiveness of EU, however, is mostly unknown in e-commerce recommendation systems. Previous research on e-commerce recommendation interprets the utility of purchase decisions either as a function of the consumed quantity of the product or as the gain of sellers/buyers in the monetary sense. As most consumers just purchase one unit of a product at a time and most alternatives have similar prices, such modeling of purchase utility is likely to be inaccurate in practice. In this paper, we interpret purchase utility as the satisfaction level a consumer gets from a product and propose a recommendation framework using EU to model consumers' behavioral patterns. We assume that consumer estimates the expected utilities of all the alternatives and choose products with maximum expected utility for each purchase. To deal with the potential psychological biases of each consumer, we introduce the usage of Probability Weight Function (PWF) and design our algorithm based on Weighted Expected Utility (WEU). Empirical study on real-world e-commerce datasets shows that our proposed ranking-based recommendation framework achieves statistically significant improvement against both classical Collaborative Filtering/Latent Factor Models and state-of-the-art deep models in top-K recommendation.

cs.IR↗

arXiv2020

Adversarial Reinforcement Learning under Partial Observability in Autonomous Computer Network Defence

Recent studies have demonstrated that reinforcement learning (RL) agents are susceptible to adversarial manipulation, similar to vulnerabilities previously demonstrated in the supervised learning setting. While most existing work studies the problem in the context of computer vision or console games, this paper focuses on reinforcement learning in autonomous cyber defence under partial observability. We demonstrate that under the black-box setting, where the attacker has no direct access to the target RL model, causative attacks---attacks that target the training process---can poison RL agents even if the attacker only has partial observability of the environment. In addition, we propose an inversion defence method that aims to apply the opposite perturbation to that which an attacker might use to generate their adversarial samples. Our experimental results illustrate that the countermeasure can effectively reduce the impact of the causative attack, while not significantly affecting the training process in non-attack scenarios.

stat.ML↗

arXiv2020

Graph Neural Networks with Continual Learning for Fake News Detection from Social Media

Although significant effort has been applied to fact-checking, the prevalence of fake news over social media, which has profound impact on justice, public trust and our society, remains a serious problem. In this work, we focus on propagation-based fake news detection, as recent studies have demonstrated that fake news and real news spread differently online. Specifically, considering the capability of graph neural networks (GNNs) in dealing with non-Euclidean data, we use GNNs to differentiate between the propagation patterns of fake and real news on social media. In particular, we concentrate on two questions: (1) Without relying on any text information, e.g., tweet content, replies and user descriptions, how accurately can GNNs identify fake news? Machine learning models are known to be vulnerable to adversarial attacks, and avoiding the dependence on text-based features can make the model less susceptible to the manipulation of advanced fake news fabricators. (2) How to deal with new, unseen data? In other words, how does a GNN trained on a given dataset perform on a new and potentially vastly different dataset? If it achieves unsatisfactory performance, how do we solve the problem without re-training the model on the entire data from scratch? We study the above questions on two datasets with thousands of labelled news items, and our results show that: (1) GNNs can achieve comparable or superior performance without any text information to state-of-the-art methods. (2) GNNs trained on a given dataset may perform poorly on new, unseen data, and direct incremental training cannot solve the problem---this issue has not been addressed in the previous work that applies GNNs for fake news detection. In order to solve the problem, we propose a method that achieves balanced performance on both existing and new datasets, by using techniques from continual learning to train GNNs incrementally.

cs.SI↗

arXiv2020

Image Analysis Enhanced Event Detection from Geo-tagged Tweet Streams

Events detected from social media streams often include early signs of accidents, crimes or disasters. Therefore, they can be used by related parties for timely and efficient response. Although significant progress has been made on event detection from tweet streams, most existing methods have not considered the posted images in tweets, which provide richer information than the text, and potentially can be a reliable indicator of whether an event occurs or not. In this paper, we design an event detection algorithm that combines textual, statistical and image information, following an unsupervised machine learning approach. Specifically, the algorithm starts with semantic and statistical analyses to obtain a list of tweet clusters, each of which corresponds to an event candidate, and then performs image analysis to separate events from non-events---a convolutional autoencoder is trained for each cluster as an anomaly detector, where a part of the images are used as the training data and the remaining images are used as the test instances. Our experiments on multiple datasets verify that when an event occurs, the mean reconstruction errors of the training and test images are much closer, compared with the case where the candidate is a non-event cluster. Based on this finding, the algorithm rejects a candidate if the difference is larger than a threshold. Experimental results over millions of tweets demonstrate that this image analysis enhanced approach can significantly increase the precision with minimum impact on the recall.

cs.SI↗

arXiv2019

Multi-spatial Scale Event Detection from Geo-tagged Tweet Streams via Power-law Verification

Compared with traditional news media, social media nowadays provides a richer and more timely source of news. We are interested in multi-spatial level event detection from geo-tagged tweet streams. Specifically, in this paper we (1) examine the statistical characteristic for the time series of the number of geo-tagged tweets posted from specific regions during a short time interval, e.g., ten seconds or one minute; (2) verify from over thirty datasets that while almost all such time series exhibit self-similarity, those that correspond to events, especially short-term and unplanned outbursts, follow a power-law distribution; (3) demonstrate that these findings can be applied to facilitate event detection from tweet streams. We propose two algorithms---Power-law basic and Power-law advanced, where Power-law basic only checks the existence of power-law distributions in the time series from tweet streams at multi-spatial scales, without looking into the content of each tweet, and Power-law advanced integrates power-law verification with semantic analysis via word embedding. Our experiments on multiple datasets show that by considering spatio-temporal statistical distributions of tweets alone, the seemingly naive algorithm of Power-law basic achieves comparable results with more advanced event detection methods, while the semantic analysis enhanced version, Power-law advanced, can significantly increase both the precision and the recall.

cs.SI↗

arXiv2018

Reinforcement Learning for Autonomous Defence in Software-Defined Networking

Despite the successful application of machine learning (ML) in a wide range of domains, adaptability---the very property that makes machine learning desirable---can be exploited by adversaries to contaminate training and evade classification. In this paper, we investigate the feasibility of applying a specific class of machine learning algorithms, namely, reinforcement learning (RL) algorithms, for autonomous cyber defence in software-defined networking (SDN). In particular, we focus on how an RL agent reacts towards different forms of causative attacks that poison its training process, including indiscriminate and targeted, white-box and black-box attacks. In addition, we also study the impact of the attack timing, and explore potential countermeasures such as adversarial training.

cs.CR↗

arXiv2017

WiBall: A Time-Reversal Focusing Ball Method for Indoor Tracking

With the development of the Internet of Things technology, indoor tracking has become a popular application nowadays, but most existing solutions can only work in line-of-sight scenarios, or require regular re-calibration. In this paper, we propose WiBall, an accurate and calibration-free indoor tracking system that can work well in non-line-of-sight based on radio signals. WiBall leverages a stationary and location-independent property of the time-reversal focusing effect of radio signals for highly accurate moving distance estimation. Together with the direction estimation based on inertial measurement unit and location correction using the constraints from the floorplan, WiBall is shown to be able to track a moving object with decimeter-level accuracy in different environments. Since WiBall can accommodate a large number of users with only a single pair of devices, it is low-cost and easily scalable, and can be a promising candidate for future indoor tracking applications.

eess.SP↗

arXiv2017

Watch Me, but Don't Touch Me! Contactless Control Flow Monitoring via Electromagnetic Emanations

Trustworthy operation of industrial control systems depends on secure and real-time code execution on the embedded programmable logic controllers (PLCs). The controllers monitor and control the critical infrastructures, such as electric power grids and healthcare platforms, and continuously report back the system status to human operators. We present Zeus, a contactless embedded controller security monitor to ensure its execution control flow integrity. Zeus leverages the electromagnetic emission by the PLC circuitry during the execution of the controller programs. Zeus's contactless execution tracking enables non-intrusive monitoring of security-critical controllers with tight real-time constraints. Those devices often cannot tolerate the cost and performance overhead that comes with additional traditional hardware or software monitoring modules. Furthermore, Zeus provides an air-gap between the monitor (trusted computing base) and the target (potentially compromised) PLC. This eliminates the possibility of the monitor infection by the same attack vectors. Zeus monitors for control flow integrity of the PLC program execution. Zeus monitors the communications between the human-machine interface and the PLC, and captures the control logic binary uploads to the PLC. Zeus exercises its feasible execution paths, and fingerprints their emissions using an external electromagnetic sensor. Zeus trains a neural network for legitimate PLC executions, and uses it at runtime to identify the control flow based on PLC's electromagnetic emissions. We implemented Zeus on a commercial Allen Bradley PLC, which is widely used in industry, and evaluated it on real-world control program executions. Zeus was able to distinguish between different legitimate and malicious executions with 98.9% accuracy and with zero overhead on PLC execution by design.

cs.CR↗

arXiv2017

The Vapor-Solid-Solid Growth of Ge Nanowires on Ge (110) by Molecular Beam Epitaxy

We demonstrate Au-assisted vapor-solid-solid (VSS) growth of Ge nanowires (NWs) by molecular beam epitaxy (MBE) at 220 °C, which is compatible with the temperature window for Si-based integrated circuit. Low temperature grown Ge NWs hold a smaller size, similar uniformity and better fit with Au tips in diameter, in contrast to Ge NWs grown at around or above the eutectic temperature of Au-Ge alloy in the vapor-liquid-solid (VLS) growth. Three growth orientations were observed on Ge (110) by the VSS growth at 220 °C, differing from only one growth direction of Ge NWs by the VLS growth at a high temperature. The evolution of NWs dimension and morphology from the VLS growth to the VSS growth is qualitatively explained via analyzing the mechanism of the two growth modes.

physics.app-ph↗

arXiv2017

Adequacy of the Gradient-Descent Method for Classifier Evasion Attacks

Despite the wide use of machine learning in adversarial settings including computer security, recent studies have demonstrated vulnerabilities to evasion attacks---carefully crafted adversarial samples that closely resemble legitimate instances, but cause misclassification. In this paper, we examine the adequacy of the leading approach to generating adversarial samples---the gradient descent approach. In particular (1) we perform extensive experiments on three datasets, MNIST, USPS and Spambase, in order to analyse the effectiveness of the gradient-descent method against non-linear support vector machines, and conclude that carefully reduced kernel smoothness can significantly increase robustness to the attack; (2) we demonstrate that separated inter-class support vectors lead to more secure models, and propose a quantity similar to margin that can efficiently predict potential susceptibility to gradient-descent attacks, before the attack is launched; and (3) we design a new adversarial sample construction algorithm based on optimising the multiplicative ratio of class decision functions.

cs.CR↗

arXiv2015

Signal Improvement and Contrast Enhancement in Magnetic Resonance Imaging

This thesis reports advances in magnetic resonance imaging (MRI), with the ultimate goal of improving signal and contrast in biomedical applications. More specifically, novel MRI pulse sequences have been designed to characterize microstructure, enhance signal and contrast in tissue, and image functional processes. In this thesis, rat brain and red bone marrow images are acquired using iMQCs (intermolecular multiple quantum coherences) between intermediate separated spins. As an important application, iMQCs images in different directions can be used for anisotropy mapping and tissue microstructure analysis. At the same time, the simulations prove that the dipolar field from the overall shape only has small contributions to the experimental iMQC signal. Besides magnitude of iMQCs, phase of iMQCs should be studied as well. The phase anisotropy maps built by our method can clearly show susceptibility information in rat brain. It may provide meaningful diagnostic information. To deeply study susceptibility, the modified-crazed sequence is developed. Combining phase data of modified-crazed images and phase data of iMQCs images is very promising to construct microstructure maps. Obviously, the phase image in all above techniques needs to be highly-contrasted and clear. To achieve the goal, algorithm tools from Susceptibility-Weighted Imaging (SWI) and Susceptibility Tensor Imaging (STI) stands out superb useful and creative in our system.

physics.med-ph↗

arXiv2013

Anisotropy mapping in rat brains using Intermolecular Multiple Quantum Coherence Effects

This document reports an unconventional and rapidly developing approach to magnetic resonance imaging (MRI) using intermolecular multiple-quantum coherences (iMQCs). Rat brain images are acquired using iMQCs. We detect iMQCs between spins that are 10 μm to 500 μm apart. The interaction between spins is dependent on different directions. We can choose the directions on physical Z, Y and X axis by choosing correlation gradients along those directions. As an important application, iMQCs can be used for anisotropy mapping. In the rat brains, we investigate tissue microstructure. We simulated images expected from rat brains without microstructure. We compare those with experimental results to prove that the dipolar field from the overall shape only has small contributions to the experimental iMQC signal. Because of the underlying low signal to noise ratio (SNR) in iMQCs, this anisotropy mapping method still has comparatively large potentials to grow. The ultimate goal of my project is to develop creative and effective methods of tissue microstructure anisotropy mapping. Recently we found that combining phase data of iMQCs images with phase data of modified-crazed images is very promising to construct microstructure maps. Some information and initial results are shown in this document.

physics.med-ph↗