arXiv subjects

Tianyi Zhang

Publications and source records attributed to Tianyi Zhang.

At least 343 records · Page 19Linked to original sources

arXiv2022

TempLM: Distilling Language Models into Template-Based Generators

While pretrained language models (PLMs) have greatly improved text generation, they have also been known to produce unfaithful or inappropriate content. In contrast, classic template-based systems provide strong guarantees of faithfulness at the cost of fluency. We propose TempLM, which achieves the best of both worlds by distilling a PLM into a template-based generator. On the E2E and SynthBio data-to-text datasets, we show that TempLM is more faithful than the original PLM and is more fluent than prior template systems. Notably, on an out-of-domain evaluation, TempLM reduces a finetuned BART model's unfaithfulness rate from 83% to 0%. In a human study, we find that TempLM's templates substantially improve upon human-written ones in BERTScore.

cs.CL↗

arXiv2022

Learning Cross-Scale Visual Representations for Real-Time Image Geo-Localization

Robot localization remains a challenging task in GPS denied environments. State estimation approaches based on local sensors, e.g. cameras or IMUs, are drifting-prone for long-range missions as error accumulates. In this study, we aim to address this problem by localizing image observations in a 2D multi-modal geospatial map. We introduce the cross-scale dataset and a methodology to produce additional data from cross-modality sources. We propose a framework that learns cross-scale visual representations without supervision. Experiments are conducted on data from two different domains, underwater and aerial. In contrast to existing studies in cross-view image geo-localization, our approach a) performs better on smaller-scale multi-modal maps; b) is more computationally efficient for real-time applications; c) can serve directly in concert with state estimation pipelines.

cs.CV↗

arXiv2022

Autonomous Investigations over WS$_2$ and Au{111} with Scanning Probe Microscopy

Individual atomic defects in 2D materials impact their macroscopic functionality. Correlating the interplay is challenging, however, intelligent hyperspectral scanning tunneling spectroscopy (STS) mapping provides a feasible solution to this technically difficult and time consuming problem. Here, dense spectroscopic volume is collected autonomously via Gaussian process regression, where convolutional neural networks are used in tandem for spectral identification. Acquired data enable defect segmentation, and a workflow is provided for machine-driven decision making during experimentation with capability for user customization. We provide a means towards autonomous experimentation for the benefit of both enhanced reproducibility and user-accessibility. Hyperspectral investigations on WS$_2$ sulfur vacancy sites are explored, which is combined with local density of states confirmation on the Au{111} herringbone reconstruction. Chalcogen vacancies, pristine WS$_2$, Au face-centered cubic, and Au hexagonal close packed regions are examined and detected by machine learning methods to demonstrate the potential of artificial intelligence for hyperspectral STS mapping.

cond-mat.mtrl-sci↗

arXiv2022

When Cyber-Physical Systems Meet AI: A Benchmark, an Evaluation, and a Way Forward

Cyber-physical systems (CPS) have been broadly deployed in safety-critical domains, such as automotive systems, avionics, medical devices, etc. In recent years, Artificial Intelligence (AI) has been increasingly adopted to control CPS. Despite the popularity of AI-enabled CPS, few benchmarks are publicly available. There is also a lack of deep understanding on the performance and reliability of AI-enabled CPS across different industrial domains. To bridge this gap, we initiate to create a public benchmark of industry-level CPS in seven domains and build AI controllers for them via state-of-the-art deep reinforcement learning (DRL) methods. Based on that, we further perform a systematic evaluation of these AI-enabled systems with their traditional counterparts to identify the current challenges and explore future opportunities. Our key findings include (1) AI controllers do not always outperform traditional controllers, (2) existing CPS testing techniques (falsification, specifically) fall short of analyzing AI-enabled CPS, and (3) building a hybrid system that strategically combines and switches between AI controllers and traditional controllers can achieve better performance across different domains. Our results highlight the need for new testing techniques for AI-enabled CPS and the need for more investigations into hybrid CPS systems to achieve optimal performance and reliability.

cs.SE↗

arXiv2022

Channel Estimation and Projection for RIS-assisted MIMO Using Zadoff-Chu Sequences

The reconfigurable intelligent surface (RIS) technology is a promising enabler for millimeter wave (mmWave) wireless communications, as it can potentially provide spectral efficiency comparable to the conventional massive multiple-input multiple-output (MIMO) but with significantly lower hardware complexity. In this paper, we focus on the estimation and projection of the uplink RIS-aided massive MIMO channel, which can be time-varying. We propose to let the user equipments (UE) transmit Zadoff-Chu (ZC) sequences and let the base station (BS) conduct maximum likelihood (ML) estimation of the uplink channel. The proposed scheme is computationally efficient: it uses ZC sequences to decouple the estimation of the frequency and time offsets; it uses the space-alternating generalized expectation-maximization (SAGE) method to reduce the high-dimensional problem due to the multipaths to multiple lower-dimensional ones per path. Owing to the estimation of the Doppler frequency offsets, the time-varying channel state can be projected, which can significantly lower the overhead of the pilots for channel estimation. The numerical simulations verify the effectiveness of the proposed scheme.

cs.IT↗

arXiv2022

Model-Based Neural Network and Its Application to Line Spectral Estimation

This paper presents the concept of "model-based neural network"(MNN), which is inspired by the classic artificial neural network (ANN) but for different usages. Instead of being used as a data-driven classifier, a MNN serves as a modeling tool with artfully defined inputs, outputs, and activation functions which have explicit physical meanings. Owing to the same layered form as an ANN, a MNN can also be optimized using the back-propagation (BP) algorithm. As an interesting application, the classic problem of line spectral estimation can be modeled by a MNN. We propose to first initialize the MNN by the fast Fourier transform (FFT) based spectral estimation, and then optimize the MNN by the BP algorithm, which automatically yields the maximum likelihood (ML) parameter estimation of the frequency spectrum. We also design a method of merging and pruning the hidden-layer nodes of the MNN, which can be used for model-order selection, i.e., to estimate the number of sinusoids. Numerical simulations verify the effectiveness of the proposed method.

eess.SP↗

arXiv2021

MSHT: Multi-stage Hybrid Transformer for the ROSE Image Analysis of Pancreatic Cancer

Pancreatic cancer is one of the most malignant cancers in the world, which deteriorates rapidly with very high mortality. The rapid on-site evaluation (ROSE) technique innovates the workflow by immediately analyzing the fast stained cytopathological images with on-site pathologists, which enables faster diagnosis in this time-pressured process. However, the wider expansion of ROSE diagnosis has been hindered by the lack of experienced pathologists. To overcome this problem, we propose a hybrid high-performance deep learning model to enable the automated workflow, thus freeing the occupation of the valuable time of pathologists. By firstly introducing the Transformer block into this field with our particular multi-stage hybrid design, the spatial features generated by the convolutional neural network (CNN) significantly enhance the Transformer global modeling. Turning multi-stage spatial features as global attention guidance, this design combines the robustness from the inductive bias of CNN with the sophisticated global modeling power of Transformer. A dataset of 4240 ROSE images is collected to evaluate the method in this unexplored field. The proposed multi-stage hybrid Transformer (MSHT) achieves 95.68% in classification accuracy, which is distinctively higher than the state-of-the-art models. Facing the need for interpretability, MSHT outperforms its counterparts with more accurate attention regions. The results demonstrate that the MSHT can distinguish cancer samples accurately at an unprecedented image scale, laying the foundation for deploying automatic decision systems and enabling the expansion of ROSE in clinical practice. The code and records are available at: https://github.com/sagizty/Multi-Stage-Hybrid-Transformer.

eess.IV↗

arXiv2021

Interference and Coverage Analysis of mmWave Inter-Vehicle Broadcast with Directional Antennas

Thanks to the availability of large bandwidth and high-gain directional antennas at the millimeter-wave (mmWave) bands, mmWave communications have been considered as one of the primary solutions to meet the high data rates needs in vehicular networks. Unicast in mmWave vehicle-to-vehicle (V2V) communications has been well-studied, but much less attention has been paid to V2V broadcast which is required by many V2V applications such as active safety. To fill the gap, this paper systematically investigates mmWave V2V broadcast by considering the unique properties of mmWave signal propagation in V2V environments as well as the impacts of directional antennas and interference. Based on widely-accepted, high-fidelity system models, we mathematically analyze the receiver-side signal-to-interference-plus-noise-ratio (SINR) and broadcast coverage, and we study the impacts of blockage, inter-vehicle distance, vehicle density and beam pattern. Through comprehensive numerical analysis, we find out that, instead of a single unique optimal beamwidth, there exists an optimal range of beamwidth, in which the beamwidths have similar performance and can maximize the coverage. We also find out that the selection of carrier sensing range plays an important role as it highly influences the performance of the whole vehicular networks. Our analysis provides unique insight into mmWave V2V broadcast, and it sheds light on designing effective V2V broadcast protocols.

cs.NI↗

arXiv2021

Rethinking Importance Weighting for Transfer Learning

A key assumption in supervised learning is that training and test data follow the same probability distribution. However, this fundamental assumption is not always satisfied in practice, e.g., due to changing environments, sample selection bias, privacy concerns, or high labeling costs. Transfer learning (TL) relaxes this assumption and allows us to learn under distribution shift. Classical TL methods typically rely on importance-weighting -- a predictor is trained based on the training losses weighted according to the importance (i.e., the test-over-training density ratio). However, as real-world machine learning tasks are becoming increasingly complex, high-dimensional, and dynamical, novel approaches are explored to cope with such challenges recently. In this article, after introducing the foundation of TL based on importance-weighting, we review recent advances based on joint and dynamic importance-predictor estimation. Furthermore, we introduce a method of causal mechanism transfer that incorporates causal structure in TL. Finally, we discuss future perspectives of TL research.

cs.LG↗

arXiv2021

Gomory-Hu Trees in Quadratic Time

Gomory-Hu tree [Gomory and Hu, 1961] is a succinct representation of pairwise minimum cuts in an undirected graph. When the input graph has general edge weights, classic algorithms need at least cubic running time to compute a Gomory-Hu tree. Very recently, the authors of [AKL+, arXiv v1, 2021] have improved the running time to $\tilde{O}(n^{2.875})$ which breaks the cubic barrier for the first time. In this paper, we refine their approach and improve the running time to $\tilde{O}(n^2)$. This quadratic upper bound is also obtained independently in an updated version by the same group of authors [AKL+, arXiv v2, 2021].

cs.DS↗

arXiv2021

Trends on 3d Transition Metal Coordination on Monolayer MoS$_2$

Two-dimensional materials (2DM) have attracted much interest due to their distinct optical, electronic, and catalytic properties. These properties can be by tuned a range of methods including substitutional doping or, as recently demonstrated, by surface functionalization with single atoms, increasing even further 2DM portfolio. Here we theoretically and experimentally describe the coordination reaction between MoS$_2$ monolayers with 3d transition metals (TMs), exploring the nature and the trend of MoS$_2$-TMs interaction. Density Functional Theory calculations, X-Ray Photoelectron Spectroscopy (XPS), and Photoluminescence (PL) point to the formation of MoS$_2$-TM coordination complexes, where the adsorption energy trend for 3d TM resembles the crystal-field (CF) stabilization energy for weak-field complexes. Pearson's theory for hard-soft acid-base and Ligand-field theory were applied to discuss the periodic trends on 3d TM coordination on the MoS$_2$ surface. We found that softer acids with higher ligand field stabilization energy, such as Ni$^{2+}$, tend to form bonds with more covalent character with MoS$_2$, which can be considered a soft base. On the other hand, harder acids, such as Cr$^{3+}$, tend to form bonds with more ionic character. Additionally, we studied the trends in charge transfer and doping observed in the XPS and PL results, where metals such as Ni led to an n-type of doping, while Cu functionalization results in p-type doping. Therefore, the formation of coordination complexes on TMD's surface is demonstrated to be a promising and effective way to control and to understand the nature of the single-atom functionalization of TMD.

cond-mat.mtrl-sci↗

arXiv2021

All lines on a smooth cubic surface in terms of three skew lines

Jordan showed that the incidence variety of a smooth cubic surface containing 27 lines has solvable Galois group over the incidence variety of a smooth cubic surface containing 3 skew lines. As noted by Harris, it follows that for any smooth cubic surface, there exist formulas for all 27 lines in terms of any 3 skew lines. In response to a question of Farb, we compute these formulas explicitly. We also discuss how these formulas relate to Schläfli's count of lines on real smooth cubic surfaces.

math.AG↗

arXiv2021

PSRR-MaxpoolNMS: Pyramid Shifted MaxpoolNMS with Relationship Recovery

Non-maximum Suppression (NMS) is an essential postprocessing step in modern convolutional neural networks for object detection. Unlike convolutions which are inherently parallel, the de-facto standard for NMS, namely GreedyNMS, cannot be easily parallelized and thus could be the performance bottleneck in convolutional object detection pipelines. MaxpoolNMS is introduced as a parallelizable alternative to GreedyNMS, which in turn enables faster speed than GreedyNMS at comparable accuracy. However, MaxpoolNMS is only capable of replacing the GreedyNMS at the first stage of two-stage detectors like Faster-RCNN. There is a significant drop in accuracy when applying MaxpoolNMS at the final detection stage, due to the fact that MaxpoolNMS fails to approximate GreedyNMS precisely in terms of bounding box selection. In this paper, we propose a general, parallelizable and configurable approach PSRR-MaxpoolNMS, to completely replace GreedyNMS at all stages in all detectors. By introducing a simple Relationship Recovery module and a Pyramid Shifted MaxpoolNMS module, our PSRR-MaxpoolNMS is able to approximate GreedyNMS more precisely than MaxpoolNMS. Comprehensive experiments show that our approach outperforms MaxpoolNMS by a large margin, and it is proven faster than GreedyNMS with comparable accuracy. For the first time, PSRR-MaxpoolNMS provides a fully parallelizable solution for customized hardware design, which can be reused for accelerating NMS everywhere.

cs.CV↗

arXiv2021

Modeling the Field Value Variations and Field Interactions Simultaneously for Fraud Detection

With the explosive growth of e-commerce, online transaction fraud has become one of the biggest challenges for e-commerce platforms. The historical behaviors of users provide rich information for digging into the users' fraud risk. While considerable efforts have been made in this direction, a long-standing challenge is how to effectively exploit internal user information and provide explainable prediction results. In fact, the value variations of same field from different events and the interactions of different fields inside one event have proven to be strong indicators for fraudulent behaviors. In this paper, we propose the Dual Importance-aware Factorization Machines (DIFM), which exploits the internal field information among users' behavior sequence from dual perspectives, i.e., field value variations and field interactions simultaneously for fraud detection. The proposed model is deployed in the risk management system of one of the world's largest e-commerce platforms, which utilize it to provide real-time transaction fraud detection. Experimental results on real industrial data from different regions in the platform clearly demonstrate that our model achieves significant improvements compared with various state-of-the-art baseline models. Moreover, the DIFM could also give an insight into the explanation of the prediction results from dual perspectives.

cs.LG↗

arXiv2021

A One-step Approach to Covariate Shift Adaptation

A default assumption in many machine learning scenarios is that the training and test samples are drawn from the same probability distribution. However, such an assumption is often violated in the real world due to non-stationarity of the environment or bias in sample selection. In this work, we consider a prevalent setting called covariate shift, where the input distribution differs between the training and test stages while the conditional distribution of the output given the input remains unchanged. Most of the existing methods for covariate shift adaptation are two-step approaches, which first calculate the importance weights and then conduct importance-weighted empirical risk minimization. In this paper, we propose a novel one-step approach that jointly learns the predictive model and the associated weights in one optimization by minimizing an upper bound of the test risk. We theoretically analyze the proposed method and provide a generalization error bound. We also empirically demonstrate the effectiveness of the proposed method.

cs.LG↗

arXiv2021

On the Inductive Bias of Masked Language Modeling: From Statistical to Syntactic Dependencies

We study how masking and predicting tokens in an unsupervised fashion can give rise to linguistic structures and downstream performance gains. Recent theories have suggested that pretrained language models acquire useful inductive biases through masks that implicitly act as cloze reductions for downstream tasks. While appealing, we show that the success of the random masking strategy used in practice cannot be explained by such cloze-like masks alone. We construct cloze-like masks using task-specific lexicons for three different classification datasets and show that the majority of pretrained performance gains come from generic masks that are not associated with the lexicon. To explain the empirical success of these generic masks, we demonstrate a correspondence between the Masked Language Model (MLM) objective and existing methods for learning statistical dependencies in graphical models. Using this, we derive a method for extracting these learned statistical dependencies in MLMs and show that these dependencies encode useful inductive biases in the form of syntactic structures. In an unsupervised parsing evaluation, simply forming a minimum spanning tree on the implied statistical dependence structure outperforms a classic method for unsupervised parsing (58.74 vs. 55.91 UUAS).

cs.CL↗

arXiv2021

Fully Dynamic Maximal Independent Set in Expected Poly-Log Update Time

In the fully dynamic maximal independent set (MIS) problem our goal is to maintain an MIS in a given graph $G$ while edges are inserted and deleted from the graph. The first non-trivial algorithm for this problem was presented by Assadi, Onak, Schieber, and Solomon [STOC 2018] who obtained a deterministic fully dynamic MIS with $O(m^{3/4})$ update time. Later, this was independently improved by Du and Zhang and by Gupta and Khan [arXiv 2018] to $\tilde{O}(m^{2/3})$ update time. Du and Zhang [arXiv 2018] also presented a randomized algorithm against an oblivious adversary with $\tilde{O}(\sqrt{m})$ update time. The current state of art is by Assadi, Onak, Schieber, and Solomon [SODA 2019] who obtained randomized algorithms against oblivious adversary with $\tilde{O}(\sqrt{n})$ and $\tilde{O}(m^{1/3})$ update times. In this paper, we propose a dynamic randomized algorithm against oblivious adversary with expected worst-case update time of $O(\log^4n)$. As a direct corollary, one can apply the black-box reduction from a recent work by Bernstein, Forster, and Henzinger [SODA 2019] to achieve $O(\log^6n)$ worst-case update time with high probability. This is the first dynamic MIS algorithm with very fast update time of poly-log.

cs.DS↗

arXiv2021

Design Paradigms Based on Spring Agonists for Underactuated Robot Hands: Concepts and Application

In this paper, we focus on a rarely used paradigm in the design of underactuated robot hands: the use of springs as agonists and tendons as antagonists. We formalize this approach in a design matrix also considering its interplay with the underactuation method used (one tendon for multiple joints vs. multiple tendons on one motor shaft). We then show how different cells in this design matrix can be combined in order to facilitate the implementation of desired postural synergies with a single motor. Furthermore, we show that when agonist and antagonist tendons are combined on the same motor shaft, the resulting spring force cancellation can be leveraged to produce multiple desirable behaviors, which we demonstrate in a physical prototype.

cs.RO↗