arXiv subjects

Haonan Wang

Publications and source records attributed to Haonan Wang.

At least 145 records · Page 8Linked to original sources

arXiv2022

Artificial Intelligence Security Competition (AISC)

The security of artificial intelligence (AI) is an important research area towards safe, reliable, and trustworthy AI systems. To accelerate the research on AI security, the Artificial Intelligence Security Competition (AISC) was organized by the Zhongguancun Laboratory, China Industrial Control Systems Cyber Emergency Response Team, Institute for Artificial Intelligence, Tsinghua University, and RealAI as part of the Zhongguancun International Frontier Technology Innovation Competition (https://www.zgc-aisc.com/en). The competition consists of three tracks, including Deepfake Security Competition, Autonomous Driving Security Competition, and Face Recognition Security Competition. This report will introduce the competition rules of these three tracks and the solutions of top-ranking teams in each track.

cs.CR↗

arXiv2022

Deep Active Learning by Leveraging Training Dynamics

Active learning theories and methods have been extensively studied in classical statistical learning settings. However, deep active learning, i.e., active learning with deep learning models, is usually based on empirical criteria without solid theoretical justification, thus suffering from heavy doubts when some of those fail to provide benefits in real applications. In this paper, by exploring the connection between the generalization performance and the training dynamics, we propose a theory-driven deep active learning method (dynamicAL) which selects samples to maximize training dynamics. In particular, we prove that the convergence speed of training and the generalization performance are positively correlated under the ultra-wide condition and show that maximizing the training dynamics leads to better generalization performance. Furthermore, to scale up to large deep neural networks and data sets, we introduce two relaxations for the subset selection problem and reduce the time complexity from polynomial to constant. Empirical results show that dynamicAL not only outperforms the other baselines consistently but also scales well on large deep learning models. We hope our work would inspire more attempts on bridging the theoretical findings of deep networks and practical impacts of deep active learning in real applications.

cs.LG↗

arXiv2022

QuantPipe: Applying Adaptive Post-Training Quantization for Distributed Transformer Pipelines in Dynamic Edge Environments

Pipeline parallelism has achieved great success in deploying large-scale transformer models in cloud environments, but has received less attention in edge environments. Unlike in cloud scenarios with high-speed and stable network interconnects, dynamic bandwidth in edge systems can degrade distributed pipeline performance. We address this issue with QuantPipe, a communication-efficient distributed edge system that introduces post-training quantization (PTQ) to compress the communicated tensors. QuantPipe uses adaptive PTQ to change bitwidths in response to bandwidth dynamics, maintaining transformer pipeline performance while incurring limited inference accuracy loss. We further improve the accuracy with a directed-search analytical clipping for integer quantization method (DS-ACIQ), which bridges the gap between estimated and real data distributions. Experimental results show that QuantPipe adapts to dynamic bandwidth to maintain pipeline performance while achieving a practical model accuracy using a wide range of quantization bitwidths, e.g., improving accuracy under 2-bit quantization by 15.85\% on ImageNet compared to naive quantization.

cs.DC↗

arXiv2022

Augmentation-Free Graph Contrastive Learning with Performance Guarantee

Graph contrastive learning (GCL) is the most representative and prevalent self-supervised learning approach for graph-structured data. Despite its remarkable success, existing GCL methods highly rely on an augmentation scheme to learn the representations invariant across different augmentation views. In this work, we revisit such a convention in GCL through examining the effect of augmentation techniques on graph data via the lens of spectral theory. We found that graph augmentations preserve the low-frequency components and perturb the middle-and high-frequency components of the graph, which contributes to the success of GCL algorithms on homophilic graphs but hinder its application on heterophilic graphs, due to the high-frequency preference of heterophilic data. Motivated by this, we propose a novel, theoretically-principled, and augmentation-free GCL method, named AF-GCL, that (1) leverages the features aggregated by Graph Neural Network to construct the self-supervision signal instead of augmentations and therefore (2) is less sensitive to the graph homophily degree. Theoretically, We present the performance guarantee for AF-GCL as well as an analysis for understanding the efficacy of AF-GCL. Extensive experiments on 14 benchmark datasets with varying degrees of heterophily show that AF-GCL presents competitive or better performance on homophilic graphs and outperforms all existing state-of-the-art GCL methods on heterophilic graphs with significantly less computational overhead.

cs.LG↗

arXiv2022

Understanding Programmatic Weak Supervision via Source-aware Influence Function

Programmatic Weak Supervision (PWS) aggregates the source votes of multiple weak supervision sources into probabilistic training labels, which are in turn used to train an end model. With its increasing popularity, it is critical to have some tool for users to understand the influence of each component (e.g., the source vote or training data) in the pipeline and interpret the end model behavior. To achieve this, we build on Influence Function (IF) and propose source-aware IF, which leverages the generation process of the probabilistic labels to decompose the end model's training objective and then calculate the influence associated with each (data, source, class) tuple. These primitive influence score can then be used to estimate the influence of individual component of PWS, such as source vote, supervision source, and training data. On datasets of diverse domains, we demonstrate multiple use cases: (1) interpreting incorrect predictions from multiple angles that reveals insights for debugging the PWS pipeline, (2) identifying mislabeling of sources with a gain of 9%-37% over baselines, and (3) improving the end model's generalization performance by removing harmful components in the training objective (13%-24% better than ordinary IF).

cs.LG↗

arXiv2022

Reconfigurable MIMO towards Electro-magnetic Information Theory: Capacity Maximization Pattern Design

In this paper, we focus on the pattern reconfigurable multiple-input multiple-output (PR-MIMO), a technique that has the potential to bridge the gap between electro-magnetics and communications towards the emerging Electro-magnetic Information Theory (EIT). Specifically, we focus on the pattern design problem aimed at maximizing the channel capacity for reconfigurable MIMO communication systems, where we firstly introduce the matrix representation of PR-MIMO and further formulate a pattern design problem. We decompose the pattern design into two steps, i.e., the correlation modification process to optimize the correlation structure of the channel, followed by the power allocation process to improve the channel quality based on the optimized channel structure. For the correlation modification process, we propose a sequential optimization framework with eigenvalue decomposition to obtain near-optimal solutions. For the power allocation process, we provide a closed-form power allocation scheme to redistribute the transmission power among the modified subchannels. Numerical results show that the proposed pattern design scheme offers significant improvements over legacy MIMO systems, which motivates the application of PR-MIMO in wireless communication systems.

cs.IT↗

arXiv2022

Realization of Kane-Mele Model in $\pmb X\bf{N_4}$-Embedded Graphene ($\pmb X$=Pt, Ir, Rh, Os)

Monolayer graphene embedded with transition metal nitride (i.e., $X$N$_4$) has been experimentally synthesized recently, where a transition metal atom together with four nitrogen atoms as a unit are embedded in graphene to form a stable planar single-atom-thick structure. We provide a systematic study on the structural, electronic and topological properties of these $X$N$_4$-embedded graphene by utilizing both first-principles calculations and tight-binding model. We find that $X$N$_4$-embedded graphene ($X$=Pt, Ir, Rh, Os) can open topologically nontrivial band gaps that host \emph{two-dimensional} $\mathbb{Z}_2$ topological insulators. We further show that the low-energy bands near the band gaps can be perfectly captured by a modified Kane-Mele model Hamiltonian. Our work not only provides concrete two-dimensional materials that are very rare to realize \emph{two-dimensional} $\mathbb{Z}_2$ topological insulators, but also makes the graphene system to be realistic in hosting Kane-Mele type $\mathbb{Z}_2$ topological insulators.

cond-mat.mtrl-sci↗

arXiv2022

UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-wise Perspective with Transformer

Most recent semantic segmentation methods adopt a U-Net framework with an encoder-decoder architecture. It is still challenging for U-Net with a simple skip connection scheme to model the global multi-scale context: 1) Not each skip connection setting is effective due to the issue of incompatible feature sets of encoder and decoder stage, even some skip connection negatively influence the segmentation performance; 2) The original U-Net is worse than the one without any skip connection on some datasets. Based on our findings, we propose a new segmentation framework, named UCTransNet (with a proposed CTrans module in U-Net), from the channel perspective with attention mechanism. Specifically, the CTrans module is an alternate of the U-Net skip connections, which consists of a sub-module to conduct the multi-scale Channel Cross fusion with Transformer (named CCT) and a sub-module Channel-wise Cross-Attention (named CCA) to guide the fused multi-scale channel-wise information to effectively connect to the decoder features for eliminating the ambiguity. Hence, the proposed connection consisting of the CCT and CCA is able to replace the original skip connection to solve the semantic gaps for an accurate automatic medical image segmentation. The experimental results suggest that our UCTransNet produces more precise segmentation performance and achieves consistent improvements over the state-of-the-art for semantic segmentation across different datasets and conventional architectures involving transformer or U-shaped framework. Code: https://github.com/McGregorWwww/UCTransNet.

cs.CV↗

arXiv2021

Acoustic topological Anderson insulators

Recent breakthrough on topological Anderson insulators revealed the breakdown of the traditional perception that sufficiently strong disorder may induce the appearance of topological protected transport states instead of destruction. Although topological Anderson insulators have been observed in various time-reversal symmetry breaking systems, the observation of topological Anderson insulators protected by time-reversal symmetry remains scarce, which are considered to be more promising in applications such as the integrated devices. Here, we report the experimental observation of topological Anderson insulator in a two-dimensional bilayer phononic crystal. The robust spin-dependent edge states, as evidence of topological Anderson insulating phase, are observed by introducing on-site disorder. In addition, spin Bott index was computed to identify the topological invariants of the system with disorder, which confirmed the occurrence of disorder-induced topological state. Our results reveal that the impurities and defects introduced in the processing of integrated devices may induce the formation of topological transport states, which are promising for the exploration of new routes for the integration devices design.

cond-mat.mes-hall↗

arXiv2021

From Intrinsic to Counterfactual: On the Explainability of Contextualized Recommender Systems

With the prevalence of deep learning based embedding approaches, recommender systems have become a proven and indispensable tool in various information filtering applications. However, many of them remain difficult to diagnose what aspects of the deep models' input drive the final ranking decision, thus, they cannot often be understood by human stakeholders. In this paper, we investigate the dilemma between recommendation and explainability, and show that by utilizing the contextual features (e.g., item reviews from users), we can design a series of explainable recommender systems without sacrificing their performance. In particular, we propose three types of explainable recommendation strategies with gradual change of model transparency: whitebox, graybox, and blackbox. Each strategy explains its ranking decisions via different mechanisms: attention weights, adversarial perturbations, and counterfactual perturbations. We apply these explainable models on five real-world data sets under the contextualized setting where users and items have explicit interactions. The empirical results show that our model achieves highly competitive ranking performance, and generates accurate and effective explanations in terms of numerous quantitative metrics and qualitative visualizations.

cs.IR↗

arXiv2021

Transfer Learning of Graph Neural Networks with Ego-graph Information Maximization

Graph neural networks (GNNs) have achieved superior performance in various applications, but training dedicated GNNs can be costly for large-scale graphs. Some recent work started to study the pre-training of GNNs. However, none of them provide theoretical insights into the design of their frameworks, or clear requirements and guarantees towards their transferability. In this work, we establish a theoretically grounded and practically useful framework for the transfer learning of GNNs. Firstly, we propose a novel view towards the essential graph information and advocate the capturing of it as the goal of transferable GNN training, which motivates the design of EGI (Ego-Graph Information maximization) to analytically achieve this goal. Secondly, when node features are structure-relevant, we conduct an analysis of EGI transferability regarding the difference between the local graph Laplacians of the source and target graphs. We conduct controlled synthetic experiments to directly justify our theoretical conclusions. Comprehensive experiments on two real-world network datasets show consistent results in the analyzed setting of direct-transfering, while those on large-scale knowledge graphs show promising results in the more practical setting of transfering with fine-tuning.

cs.LG↗

arXiv2021

Controllable Gradient Item Retrieval

In this paper, we identify and study an important problem of gradient item retrieval. We define the problem as retrieving a sequence of items with a gradual change on a certain attribute, given a reference item and a modification text. For example, after a customer saw a white dress, she/he wants to buy a similar one but more floral on it. The extent of "more floral" is subjective, thus prompting one floral dress is hard to satisfy the customer's needs. A better way is to present a sequence of products with increasingly floral attributes based on the white dress, and allow the customer to select the most satisfactory one from the sequence. Existing item retrieval methods mainly focus on whether the target items appear at the top of the retrieved sequence, but ignore the demand for retrieving a sequence of products with gradual change on a certain attribute. To deal with this problem, we propose a weakly-supervised method that can learn a disentangled item representation from user-item interaction data and ground the semantic meaning of attributes to dimensions of the item representation. Our method takes a reference item and a modification as a query. During inference, we start from the reference item and "walk" along the direction of the modification in the item representation space to retrieve a sequence of items in a gradient manner. We demonstrate our proposed method can achieve disentanglement through weak supervision. Besides, we empirically show that an item sequence retrieved by our method is gradually changed on an indicated attribute and, in the item retrieval task, our method outperforms existing approaches on three different datasets.

cs.IR↗

arXiv2021

Secure Deep Graph Generation with Link Differential Privacy

Many data mining and analytical tasks rely on the abstraction of networks (graphs) to summarize relational structures among individuals (nodes). Since relational data are often sensitive, we aim to seek effective approaches to generate utility-preserved yet privacy-protected structured data. In this paper, we leverage the differential privacy (DP) framework to formulate and enforce rigorous privacy constraints on deep graph generation models, with a focus on edge-DP to guarantee individual link privacy. In particular, we enforce edge-DP by injecting proper noise to the gradients of a link reconstruction-based graph generation model, while ensuring data utility by improving structure learning with structure-oriented graph discrimination. Extensive experiments on two real-world network datasets show that our proposed DPGGAN model is able to generate graphs with effectively preserved global structure and rigorously protected individual link privacy.

cs.SI↗

arXiv2020

Determination of Dielectric Functions and Exciton Oscillator Strength of Two-Dimensional Hybrid Perovskites

Two-dimensional (2D) hybrid organic inorganic perovskite (HOIP) semiconductors have attracted widespread attention as a platform of next generation optoelectronic devices benefiting from their naturally occurring and tunable multiple quantum-well like (QW) structures, which enable a wide range of physical properties. Determining the intrinsic optical/electronic properties of 2D HOIPs is extremely important for further utility in photonic and optoelectronics devices. Here, we obtain the optical dielectric functions, complex refractive indices, and complex optical conductivities of both Ruddlesden-Popper (RP) and Dion-Jacobsen (DJ) phases of 2D HOIPs as a function of the perovskite QW thickness via spectroscopic ellipsometry over a broad energy range of 0.73 - 3.34 eV. We identify a series of feature peaks in the dielectric functions, and explain the evolution of ground state exciton peak with unit cell thickness and changing excitonic confinement. We observe extraordinary values of optical extinction and electric loss tangents at the primary excitonic resonances and provide their detailed comparison with other known excitonic materials. Our study is expected to lay foundation for understanding optical properties of pure phase 2D HOIPs, which will be helpful for the accurate modelling of their photonics and optoelectronic devices.

physics.app-ph↗

arXiv2020

Giant gate-tunability of complex refractive index in semiconducting carbon nanotubes

Electrically-tunable optical properties in materials are desirable for many applications ranging from displays to lasing and optical communication. In most two-dimensional thin-films and other quantum confined materials, these constants have been measured accurately. However, the optical constants of single wall nanotubes (SWCNT) as a function of electrostatic tuning are yet to be measured due to lack of electronic purity and spatial homogeneity over large areas. Here, we measure the basic optical constants of ultrathin high-purity (>99%) semiconducting single wall carbon nanotube (s-SWCNT) films with spectroscopic ellipsometry. We extract the gate-tunable complex refractive index of s-SWCNT films and observe giant modulation of the real refractive index (~11.2% or an absolute value of >0.2) and extinction coefficient (~11.6%) in the near-infrared (IR) region (1.3-1.55 μm) induced by the applied electric field significantly higher than all existing electro-optic semiconductors in this wavelength range. We further design a multilayer IR reflection phase modulator stack by combining s-SWCNT and monolayer MoS2 heterostructures that can attain >45° reflection phase modulation at 1600 nm wavelength for < 200 nm total stack thickness. Our results highlight s-SWCNT as a promising material system for infrared photonics and electro-optics in telecommunication applications.

physics.optics↗

arXiv2019

Relation Learning on Social Networks with Multi-Modal Graph Edge Variational Autoencoders

While node semantics have been extensively explored in social networks, little research attention has been paid to profile edge semantics, i.e., social relations. Ideal edge semantics should not only show that two users are connected, but also why they know each other and what they share in common. However, relations in social networks are often hard to profile, due to noisy multi-modal signals and limited user-generated ground-truth labels. In this work, we aim to develop a unified and principled framework that can profile user relations as edge semantics in social networks by integrating multi-modal signals in the presence of noisy and incomplete data. Our framework is also flexible towards limited or missing supervision. Specifically, we assume a latent distribution of multiple relations underlying each user link, and learn them with multi-modal graph edge variational autoencoders. We encode the network data with a graph convolutional network, and decode arbitrary signals with multiple reconstruction networks. Extensive experiments and case studies on two public DBLP author networks and two internal LinkedIn member networks demonstrate the superior effectiveness and efficiency of our proposed model.

cs.SI↗

arXiv2019

Design Light-weight 3D Convolutional Networks for Video Recognition Temporal Residual, Fully Separable Block, and Fast Algorithm

Deep 3-dimensional (3D) Convolutional Network (ConvNet) has shown promising performance on video recognition tasks because of its powerful spatio-temporal information fusion ability. However, the extremely intensive requirements on memory access and computing power prohibit it from being used in resource-constrained scenarios, such as portable and edge devices. So in this paper, we first propose a two-stage Fully Separable Block (FSB) to significantly compress the model sizes of 3D ConvNets. Then a feature enhancement approach named Temporal Residual Gradient (TRG) is developed to improve the performance of compressed model on video tasks, which provides higher accuracy, faster convergency and better robustness. Moreover, in order to further decrease the computing workload, we propose a hybrid Fast Algorithm (hFA) to drastically reduce the computation complexity of convolutions. These methods are effectively combined to design a light-weight and efficient ConvNet for video recognition tasks. Experiments on the popular dataset report 2.3x compression rate, 3.6x workload reduction, and 6.3% top-1 accuracy gain, over the state-of-the-art SlowFast model, which is already a highly compact model. The proposed methods also show good adaptability on traditional 3D ConvNet, demonstrating 7.4x more compact model, 11.0x less workload, and 3.0% higher accuracy

cs.CV↗

arXiv2015

A Smooth and Locally Sparse Estimator for Functional Linear Regression via Functional SCAD Penalty

In this paper, we propose a new regularization technique called "functional SCAD". We then combine this technique with the smoothing spline method to develop a smooth and locally sparse (i.e., zero on some sub-regions) estimator for the coefficient function in functional linear regression. The functional SCAD has a nice shrinkage property that enables our estimating procedure to identify the null subregions of the coefficient function without over shrinking the non-zero values of the coefficient function. Additionally, the smoothness of our estimated coefficient function is regularized by a roughness penalty rather than by controlling the number of knots. Our method is more theoretically sound and is computationally simpler than the other available methods. An asymptotic analysis shows that our estimator is consistent and can identify the null region with the probability tending to one. Furthermore, simulation studies show that our estimator has superior numerical performance. Finally, the practical merit of our method is demonstrated on two real applications.

math.ST↗