arXiv subjects

Han Liu

Publications and source records attributed to Han Liu.

At least 271 records · Page 15Linked to original sources

arXiv2022

A Multi-rater Comparative Study of Automatic Target Localization Methods for Epilepsy Deep Brain Stimulation Procedures

Epilepsy is the fourth most common neurological disorder and affects people of all ages worldwide. Deep Brain Stimulation (DBS) has emerged as an alternative treatment option when anti-epileptic drugs or resective surgery cannot lead to satisfactory outcomes. To facilitate the planning of the procedure and for its standardization, it is desirable to develop an algorithm to automatically localize the DBS stimulation target, i.e., Anterior Nucleus of Thalamus (ANT), which is a challenging target to plan. In this work, we perform an extensive comparative study by benchmarking various localization methods for ANT-DBS. Specifically, the methods involved in this study include traditional registration method and deep-learning-based methods including heatmap matching and differentiable spatial to numerical transform (DSNT). Our experimental results show that the deep-learning (DL)-based localization methods that are trained with pseudo labels can achieve a performance that is comparable to the inter-rater and intra-rater variability and that they are orders of magnitude faster than traditional methods.

eess.IV↗

arXiv2022

Unsupervised Domain Adaptation for Vestibular Schwannoma and Cochlea Segmentation via Semi-supervised Learning and Label Fusion

Automatic methods to segment the vestibular schwannoma (VS) tumors and the cochlea from magnetic resonance imaging (MRI) are critical to VS treatment planning. Although supervised methods have achieved satisfactory performance in VS segmentation, they require full annotations by experts, which is laborious and time-consuming. In this work, we aim to tackle the VS and cochlea segmentation problem in an unsupervised domain adaptation setting. Our proposed method leverages both the image-level domain alignment to minimize the domain divergence and semi-supervised training to further boost the performance. Furthermore, we propose to fuse the labels predicted from multiple models via noisy label correction. In the MICCAI 2021 crossMoDA challenge, our results on the final evaluation leaderboard showed that our proposed method has achieved promising segmentation performance with mean dice score of 79.9% and 82.5% and ASSD of 1.29 mm and 0.18 mm for VS tumor and cochlea, respectively. The cochlea ASSD achieved by our method has outperformed all other competing methods as well as the supervised nnU-Net.

cs.CV↗

arXiv2022

Review Polarity-wise Recommender

Utilizing review information to enhance recommendation, the de facto review-involved recommender systems, have received increasing interests over the past few years. Thereinto, one advanced branch is to extract salient aspects from textual reviews (i.e., the item attributes that users express) and combine them with the matrix factorization technique. However, existing approaches all ignore the fact that semantically different reviews often include opposite aspect information. In particular, positive reviews usually express aspects that users prefer, while negative ones describe aspects that users reject. As a result, it may mislead the recommender systems into making incorrect decisions pertaining to user preference modeling. Towards this end, in this paper, we propose a Review Polarity-wise Recommender model, dubbed as RPR, to discriminately treat reviews with different polarities. To be specific, in this model, positive and negative reviews are separately gathered and utilized to model the user-preferred and user-rejected aspects, respectively. Besides, in order to overcome the imbalance problem of semantically different reviews, we also develop an aspect-aware importance weighting approach to align the aspect importance for these two kinds of reviews. Extensive experiments conducted on eight benchmark datasets have demonstrated the superiority of our model as compared to a series of state-of-the-art review-involved baselines. Moreover, our method can provide certain explanations to the real-world rating prediction scenarios.

cs.IR↗

arXiv2021

A $χ^{(2)}$-based AlGaAs Phase Sensitive Amplifier with Record Gain, Noise and Sensitivity

Phase sensitive amplifiers (PSAs) have the potential to empower substantial advances in emerging generations of optical communication systems as well as classical and quantum on-chip signal processing. The core building block of a PSA is a nonlinear medium. While the second-order nonlinearity ($χ^{(2)}$) is stronger than the third-order nonlinearity ($χ^{(3)}$), it is used less often in semiconductors for parametric amplification owing to the challenges of effectively phase matching the interacting waves as well as two-photon absorption of the pump. In this work, we demonstrate the successful design, fabrication, and characterization of the first $χ^{(2)}$-based semiconductor PSA using an efficient phase matching approach and a pulsed pump, based on an aluminium gallium arsenide (AlGaAs) waveguide platform. Non-centrosymmetric semiconductors such as AlGaAs offer appreciable $χ^{(2)}$. Such waveguides also achieve more than one order of magnitude greater pump field confinement when compared to other materials with large $χ^{(2)}$ such as Periodically Poled Lithium Niobate (PPLN). Our AlGaAs PSA achieves an on-chip in-phase gain, a sensitivity of 0.005 photons per pulse, and approaches theoretical minimal noise figure (NF) of 0~dB. With the capability of operating on signal states with sub-single photons per pulse, our PSA could usher in a new era of on-chip quantum circuits.

physics.optics↗

arXiv2021

Trusted And Confidential Program Analysis

We develop the concept of Trusted and Confidential Program Analysis (TCPA) which enables program certification to be used where previously there was insufficient trust. Imagine a scenario where a producer may not be trusted to certify its own software (perhaps by a foreign regulator), and the producer is unwilling to release its sources and detailed design to any external body. We present a protocol that can, using trusted computing based on encrypted sources, create certification via which all can trust the delivered object code without revealing the unencrypted sources to any party. Furthermore, we describe a realization of TCPA with trusted execution environments (TEE) that enables general and efficient computation. We have implemented the TCPA protocol in a system called TCWasm for web assembly architectures. In our evaluation with 33 benchmark cases, TCWasm managed to finish the analysis with relatively slight overheads.

cs.CR↗

arXiv2021

Cross-Modality Domain Adaptation for Vestibular Schwannoma and Cochlea Segmentation

Automatic methods to segment the vestibular schwannoma (VS) tumors and the cochlea from magnetic resonance imaging (MRI) are critical to VS treatment planning. Although supervised methods have achieved satisfactory performance in VS segmentation, they require full annotations by experts, which is laborious and time-consuming. In this work, we aim to tackle the VS and cochlea segmentation problem in an unsupervised domain adaptation setting. Our proposed method leverages both the image-level domain alignment to minimize the domain divergence and semi-supervised training to further boost the performance. Furthermore, we propose to fuse the labels predicted from multiple models via noisy label correction. Our results on the challenge validation leaderboard showed that our unsupervised method has achieved promising VS and cochlea segmentation performance with mean dice score of 0.8261 $\pm$ 0.0416; The mean dice value for the tumor is 0.8302 $\pm$ 0.0772. This is comparable to the weakly-supervised based method.

eess.IV↗

arXiv2021

A Survey on Epistemic (Model) Uncertainty in Supervised Learning: Recent Advances and Applications

Quantifying the uncertainty of supervised learning models plays an important role in making more reliable predictions. Epistemic uncertainty, which usually is due to insufficient knowledge about the model, can be reduced by collecting more data or refining the learning models. Over the last few years, scholars have proposed many epistemic uncertainty handling techniques which can be roughly grouped into two categories, i.e., Bayesian and ensemble. This paper provides a comprehensive review of epistemic uncertainty learning techniques in supervised learning over the last five years. As such, we, first, decompose the epistemic uncertainty into bias and variance terms. Then, a hierarchical categorization of epistemic uncertainty learning techniques along with their representative models is introduced. In addition, several applications such as computer vision (CV) and natural language processing (NLP) are presented, followed by a discussion on research gaps and possible future research directions.

cs.LG↗

arXiv2021

Cross-Dataset Collaborative Learning for Semantic Segmentation in Autonomous Driving

Semantic segmentation is an important task for scene understanding in self-driving cars and robotics, which aims to assign dense labels for all pixels in the image. Existing work typically improves semantic segmentation performance by exploring different network architectures on a target dataset. Little attention has been paid to build a unified system by simultaneously learning from multiple datasets due to the inherent distribution shift across different datasets. In this paper, we propose a simple, flexible, and general method for semantic segmentation, termed Cross-Dataset Collaborative Learning (CDCL). Our goal is to train a unified model for improving the performance in each dataset by leveraging information from all the datasets. Specifically, we first introduce a family of Dataset-Aware Blocks (DAB) as the fundamental computing units of the network, which help capture homogeneous convolutional representations and heterogeneous statistics across different datasets. Second, we present a Dataset Alternation Training (DAT) mechanism to facilitate the collaborative optimization procedure. We conduct extensive evaluations on diverse semantic segmentation datasets for autonomous driving. Experiments demonstrate that our method consistently achieves notable improvements over prior single-dataset and cross-dataset training methods without introducing extra FLOPs. Particularly, with the same architecture of PSPNet (ResNet-18), our method outperforms the single-dataset baseline by 5.65\%, 6.57\%, and 5.79\% mIoU on the validation sets of Cityscapes, BDD100K, CamVid, respectively. We also apply CDCL for point cloud 3D semantic segmentation and achieve improved performance, which further validates the superiority and generality of our method. Code and models will be released.

cs.CV↗

arXiv2021

An Explicit-Joint and Supervised-Contrastive Learning Framework for Few-Shot Intent Classification and Slot Filling

Intent classification (IC) and slot filling (SF) are critical building blocks in task-oriented dialogue systems. These two tasks are closely-related and can flourish each other. Since only a few utterances can be utilized for identifying fast-emerging new intents and slots, data scarcity issue often occurs when implementing IC and SF. However, few IC/SF models perform well when the number of training samples per class is quite small. In this paper, we propose a novel explicit-joint and supervised-contrastive learning framework for few-shot intent classification and slot filling. Its highlights are as follows. (i) The model extracts intent and slot representations via bidirectional interactions, and extends prototypical network to achieve explicit-joint learning, which guarantees that IC and SF tasks can mutually reinforce each other. (ii) The model integrates with supervised contrastive learning, which ensures that samples from same class are pulled together and samples from different classes are pushed apart. In addition, the model follows a not common but practical way to construct the episode, which gets rid of the traditional setting with fixed way and shot, and allows for unbalanced datasets. Extensive experiments on three public datasets show that our model can achieve promising performance.

cs.CL↗

arXiv2021

Understanding the Effect of Out-of-distribution Examples and Interactive Explanations on Human-AI Decision Making

Although AI holds promise for improving human decision making in societally critical domains, it remains an open question how human-AI teams can reliably outperform AI alone and human alone in challenging prediction tasks (also known as complementary performance). We explore two directions to understand the gaps in achieving complementary performance. First, we argue that the typical experimental setup limits the potential of human-AI teams. To account for lower AI performance out-of-distribution than in-distribution because of distribution shift, we design experiments with different distribution types and investigate human performance for both in-distribution and out-of-distribution examples. Second, we develop novel interfaces to support interactive explanations so that humans can actively engage with AI assistance. Using virtual pilot studies and large-scale randomized experiments across three tasks, we demonstrate a clear difference between in-distribution and out-of-distribution, and observe mixed results for interactive explanations: while interactive explanations improve human perception of AI assistance's usefulness, they may reinforce human biases and lead to limited performance improvement. Overall, our work points out critical challenges and future directions towards enhancing human performance with AI assistance.

cs.AI↗

arXiv2021

Optimal Covariate Balancing Conditions in Propensity Score Estimation

Inverse probability of treatment weighting (IPTW) is a popular method for estimating the average treatment effect (ATE). However, empirical studies show that the IPTW estimators can be sensitive to the misspecification of the propensity score model. To address this problem, researchers have proposed to estimate propensity score by directly optimizing the balance of pre-treatment covariates. While these methods appear to empirically perform well, little is known about how the choice of balancing conditions affects their theoretical properties. To fill this gap, we first characterize the asymptotic bias and efficiency of the IPTW estimator based on the Covariate Balancing Propensity Score (CBPS) methodology under local model misspecification. Based on this analysis, we show how to optimally choose the covariate balancing functions and propose an optimal CBPS-based IPTW estimator. This estimator is doubly robust; it is consistent for the ATE if either the propensity score model or the outcome model is correct. In addition, the proposed estimator is locally semiparametric efficient when both models are correctly specified. To further relax the parametric assumptions, we extend our method by using a sieve estimation approach. We show that the resulting estimator is globally efficient under a set of much weaker assumptions and has a smaller asymptotic bias than the existing estimators. Finally, we evaluate the finite sample performance of the proposed estimators via simulation and empirical studies. An open-source software package is available for implementing the proposed methods.

stat.ME↗

arXiv2021

CLOAK: A Framework For Development of Confidential Blockchain Smart Contracts

In recent years, as blockchain adoption has been expanding across a wide range of domains, e.g., digital asset, supply chain finance, etc., the confidentiality of smart contracts is now a fundamental demand for practical applications. However, while new privacy protection techniques keep coming out, how existing ones can best fit development settings is little studied. Suffering from limited architectural support in terms of programming interfaces, state-of-the-art solutions can hardly reach general developers. In this paper, we proposed the CLOAK framework for developing confidential smart contracts. The key capability of CLOAK is allowing developers to implement and deploy practical solutions to multi-party transaction (MPT) problems, i.e., transact with secret inputs and states owned by different parties by simply specifying it. To this end, CLOAK introduced a domain-specific annotation language for declaring privacy specifications and further automatically generating confidential smart contracts to be deployed with trusted execution environment (TEE) on blockchain. In our evaluation on both simple and real-world applications, developers managed to deploy business services on blockchain in a concise manner by only developing CLOAK smart contracts whose size is less than 30% of the deployed ones.

cs.CR↗

arXiv2021

Dimensionwise Separable 2-D Graph Convolution for Unsupervised and Semi-Supervised Learning on Graphs

Graph convolutional neural networks (GCN) have been the model of choice for graph representation learning, which is mainly due to the effective design of graph convolution that computes the representation of a node by aggregating those of its neighbors. However, existing GCN variants commonly use 1-D graph convolution that solely operates on the object link graph without exploring informative relational information among object attributes. This significantly limits their modeling capability and may lead to inferior performance on noisy and sparse real-world networks. In this paper, we explore 2-D graph convolution to jointly model object links and attribute relations for graph representation learning. Specifically, we propose a computationally efficient dimensionwise separable 2-D graph convolution (DSGC) for filtering node features. Theoretically, we show that DSGC can reduce intra-class variance of node features on both the object dimension and the attribute dimension to learn more effective representations. Empirically, we demonstrate that by modeling attribute relations, DSGC achieves significant performance gain over state-of-the-art methods for node classification and clustering on a variety of real-world networks. The source code for reproducing the experimental results is available at https://github.com/liqimai/DSGC.

cs.LG↗

arXiv2021

Trade the Event: Corporate Events Detection for News-Based Event-Driven Trading

In this paper, we introduce an event-driven trading strategy that predicts stock movements by detecting corporate events from news articles. Unlike existing models that utilize textual features (e.g., bag-of-words) and sentiments to directly make stock predictions, we consider corporate events as the driving force behind stock movements and aim to profit from the temporary stock mispricing that may occur when corporate events take place. The core of the proposed strategy is a bi-level event detection model. The low-level event detector identifies events' existences from each token, while the high-level event detector incorporates the entire article's representation and the low-level detected results to discover events at the article-level. We also develop an elaborately-annotated dataset EDT for corporate event detection and news-based stock prediction benchmark. EDT includes 9721 news articles with token-level event labels as well as 303893 news articles with minute-level timestamps and comprehensive stock price labels. Experiments on EDT indicate that the proposed strategy outperforms all the baselines in winning rate, excess returns over the market, and the average return on each transaction.

cs.CL↗

arXiv2021

Linear damping and depletion in flowing plasma with strong sheared magnetic fields

In this paper, we study the long-time behavior of the solution for the linearized ideal MHD around sheared velocity and magnetic field under Stern stability condition. We prove that the velocity and magnetic field will converge to sheared velocity and magnetic field as time approaches infinity. Moreover a new depletion phenomenon is proved: the horizontal velocity and magnetic field at the critical points will decay to 0 as time approaches infinity.

math.AP↗

arXiv2021

BLOCKEYE: Hunting For DeFi Attacks on Blockchain

Decentralized finance, i.e., DeFi, has become the most popular type of application on many public blockchains (e.g., Ethereum) in recent years. Compared to the traditional finance, DeFi allows customers to flexibly participate in diverse blockchain financial services (e.g., lending, borrowing, collateralizing, exchanging etc.) via smart contracts at a relatively low cost of trust. However, the open nature of DeFi inevitably introduces a large attack surface, which is a severe threat to the security of participants funds. In this paper, we proposed BLOCKEYE, a real-time attack detection system for DeFi projects on the Ethereum blockchain. Key capabilities provided by BLOCKEYE are twofold: (1) Potentially vulnerable DeFi projects are identified based on an automatic security analysis process, which performs symbolic reasoning on the data flow of important service states, e.g., asset price, and checks whether they can be externally manipulated. (2) Then, a transaction monitor is installed offchain for a vulnerable DeFi project. Transactions sent not only to that project but other associated projects as well are collected for further security analysis. A potential attack is flagged if a violation is detected on a critical invariant configured in BLOCKEYE, e.g., Benefit is achieved within a very short time and way much bigger than the cost. We applied BLOCKEYE in several popular DeFi projects and managed to discover potential security attacks that are unreported before. A video of BLOCKEYE is available at https://youtu.be/7DjsWBLdlQU.

cs.CR↗

arXiv2021

Converse, Focus and Guess -- Towards Multi-Document Driven Dialogue

We propose a novel task, Multi-Document Driven Dialogue (MD3), in which an agent can guess the target document that the user is interested in by leading a dialogue. To benchmark progress, we introduce a new dataset of GuessMovie, which contains 16,881 documents, each describing a movie, and associated 13,434 dialogues. Further, we propose the MD3 model. Keeping guessing the target document in mind, it converses with the user conditioned on both document engagement and user feedback. In order to incorporate large-scale external documents into the dialogue, it pretrains a document representation which is sensitive to attributes it talks about an object. Then it tracks dialogue state by detecting evolvement of document belief and attribute belief, and finally optimizes dialogue policy in principle of entropy decreasing and reward increasing, which is expected to successfully guess the user's target in a minimum number of turns. Experiments show that our method significantly outperforms several strong baseline methods and is very close to human's performance.

cs.CL↗

arXiv2021

High-Temperature Structure Detection in Ferromagnets

This paper studies structure detection problems in high temperature ferromagnetic (positive interaction only) Ising models. The goal is to distinguish whether the underlying graph is empty, i.e., the model consists of independent Rademacher variables, versus the alternative that the underlying graph contains a subgraph of a certain structure. We give matching upper and lower minimax bounds under which testing this problem is possible/impossible respectively. Our results reveal that a key quantity called graph arboricity drives the testability of the problem. On the computational front, under a conjecture of the computational hardness of sparse principal component analysis, we prove that, unless the signal is strong enough, there are no polynomial time tests which are capable of testing this problem. In order to prove this result we exhibit a way to give sharp inequalities for the even moments of sums of i.i.d. Rademacher random variables which may be of independent interest.

math.ST↗