arXiv subjects

Mingyang Zhang

Publications and source records attributed to Mingyang Zhang.

At least 55 records · Page 3Linked to original sources

arXiv2023

Creator Context for Tweet Recommendation

When discussing a tweet, people usually not only refer to the content it delivers, but also to the person behind the tweet. In other words, grounding the interpretation of the tweet in the context of its creator plays an important role in deciphering the true intent and the importance of the tweet. In this paper, we attempt to answer the question of how creator context should be used to advance tweet understanding. Specifically, we investigate the usefulness of different types of creator context, and examine different model structures for incorporating creator context in tweet modeling. We evaluate our tweet understanding models on a practical use case -- recommending relevant tweets to news articles. This use case already exists in popular news apps, and can also serve as a useful assistive tool for journalists. We discover that creator context is essential for tweet understanding, and can improve application metrics by a large margin. However, we also observe that not all creator contexts are equal. Creator context can be time sensitive and noisy. Careful creator context selection and deliberate model structure design play an important role in creator context effectiveness.

cs.IR↗

arXiv2023

Privacy-preserving design of graph neural networks with applications to vertical federated learning

The paradigm of vertical federated learning (VFL), where institutions collaboratively train machine learning models via combining each other's local feature or label information, has achieved great success in applications to financial risk management (FRM). The surging developments of graph representation learning (GRL) have opened up new opportunities for FRM applications under FL via efficiently utilizing the graph-structured data generated from underlying transaction networks. Meanwhile, transaction information is often considered highly sensitive. To prevent data leakage during training, it is critical to develop FL protocols with formal privacy guarantees. In this paper, we present an end-to-end GRL framework in the VFL setting called VESPER, which is built upon a general privatization scheme termed perturbed message passing (PMP) that allows the privatization of many popular graph neural architectures.Based on PMP, we discuss the strengths and weaknesses of specific design choices of concrete graph neural architectures and provide solutions and improvements for both dense and sparse graphs. Extensive empirical evaluations over both public datasets and an industry dataset demonstrate that VESPER is capable of training high-performance GNN models over both sparse and dense graphs under reasonable privacy budgets.

cs.LG↗

arXiv2023

Automated Evaluation of Personalized Text Generation using Large Language Models

Personalized text generation presents a specialized mechanism for delivering content that is specific to a user's personal context. While the research progress in this area has been rapid, evaluation still presents a challenge. Traditional automated metrics such as BLEU and ROUGE primarily measure lexical similarity to human-written references, and are not able to distinguish personalization from other subtle semantic aspects, thus falling short of capturing the nuances of personalized generated content quality. On the other hand, human judgments are costly to obtain, especially in the realm of personalized evaluation. Inspired by these challenges, we explore the use of large language models (LLMs) for evaluating personalized text generation, and examine their ability to understand nuanced user context. We present AuPEL, a novel evaluation method that distills three major semantic aspects of the generated text: personalization, quality and relevance, and automatically measures these aspects. To validate the effectiveness of AuPEL, we design carefully controlled experiments and compare the accuracy of the evaluation judgments made by LLMs versus that of judgements made by human annotators, and conduct rigorous analyses of the consistency and sensitivity of the proposed metric. We find that, compared to existing evaluation metrics, AuPEL not only distinguishes and ranks models based on their personalization abilities more accurately, but also presents commendable consistency and efficiency for this task. Our work suggests that using LLMs as the evaluators of personalized text generation is superior to traditional text similarity metrics, even though interesting new challenges still remain.

cs.CL↗

arXiv2023

Teach LLMs to Personalize -- An Approach inspired by Writing Education

Personalized text generation is an emerging research area that has attracted much attention in recent years. Most studies in this direction focus on a particular domain by designing bespoke features or models. In this work, we propose a general approach for personalized text generation using large language models (LLMs). Inspired by the practice of writing education, we develop a multistage and multitask framework to teach LLMs for personalized generation. In writing instruction, the task of writing from sources is often decomposed into multiple steps that involve finding, evaluating, summarizing, synthesizing, and integrating information. Analogously, our approach to personalized text generation consists of multiple stages: retrieval, ranking, summarization, synthesis, and generation. In addition, we introduce a multitask setting that helps the model improve its generation ability further, which is inspired by the observation in education that a student's reading proficiency and writing ability are often correlated. We evaluate our approach on three public datasets, each of which covers a different and representative domain. Our results show significant improvements over a variety of baselines.

cs.CL↗

arXiv2023

ShiftNAS: Improving One-shot NAS via Probability Shift

One-shot Neural architecture search (One-shot NAS) has been proposed as a time-efficient approach to obtain optimal subnet architectures and weights under different complexity cases by training only once. However, the subnet performance obtained by weight sharing is often inferior to the performance achieved by retraining. In this paper, we investigate the performance gap and attribute it to the use of uniform sampling, which is a common approach in supernet training. Uniform sampling concentrates training resources on subnets with intermediate computational resources, which are sampled with high probability. However, subnets with different complexity regions require different optimal training strategies for optimal performance. To address the problem of uniform sampling, we propose ShiftNAS, a method that can adjust the sampling probability based on the complexity of subnets. We achieve this by evaluating the performance variation of subnets with different complexity and designing an architecture generator that can accurately and efficiently provide subnets with the desired complexity. Both the sampling probability and the architecture generator can be trained end-to-end in a gradient-based manner. With ShiftNAS, we can directly obtain the optimal model architecture and parameters for a given computational complexity. We evaluate our approach on multiple visual network models, including convolutional neural networks (CNNs) and vision transformers (ViTs), and demonstrate that ShiftNAS is model-agnostic. Experimental results on ImageNet show that ShiftNAS can improve the performance of one-shot NAS without additional consumption. Source codes are available at https://github.com/bestfleer/ShiftNAS.

cs.CV↗

arXiv2023

High-Quality Automatic Voice Over with Accurate Alignment: Supervision through Self-Supervised Discrete Speech Units

The goal of Automatic Voice Over (AVO) is to generate speech in sync with a silent video given its text script. Recent AVO frameworks built upon text-to-speech synthesis (TTS) have shown impressive results. However, the current AVO learning objective of acoustic feature reconstruction brings in indirect supervision for inter-modal alignment learning, thus limiting the synchronization performance and synthetic speech quality. To this end, we propose a novel AVO method leveraging the learning objective of self-supervised discrete speech unit prediction, which not only provides more direct supervision for the alignment learning, but also alleviates the mismatch between the text-video context and acoustic features. Experimental results show that our proposed method achieves remarkable lip-speech synchronization and high speech quality by outperforming baselines in both objective and subjective evaluations. Code and speech samples are publicly available.

eess.AS↗

arXiv2023

Accented Text-to-Speech Synthesis with Limited Data

This paper presents an accented text-to-speech (TTS) synthesis framework with limited training data. We study two aspects concerning accent rendering: phonetic (phoneme difference) and prosodic (pitch pattern and phoneme duration) variations. The proposed accented TTS framework consists of two models: an accented front-end for grapheme-to-phoneme (G2P) conversion and an accented acoustic model with integrated pitch and duration predictors for phoneme-to-Mel-spectrogram prediction. The accented front-end directly models the phonetic variation, while the accented acoustic model explicitly controls the prosodic variation. Specifically, both models are first pre-trained on a large amount of data, then only the accent-related layers are fine-tuned on a limited amount of data for the target accent. In the experiments, speech data of three English accents, i.e., General American English, Irish English, and British English Received Pronunciation, are used for pre-training. The pre-trained models are then fine-tuned with Scottish and General Australian English accents, respectively. Both objective and subjective evaluation results show that the accented TTS front-end fine-tuned with a small accented phonetic lexicon (5k words) effectively handles the phonetic variation of accents, while the accented TTS acoustic model fine-tuned with a limited amount of accented speech data (approximately 3 minutes) effectively improves the prosodic rendering including pitch and duration. The overall accent modeling contributes to improved speech quality and accent similarity.

eess.AS↗

arXiv2023

A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation from a Single RGB Image

3D interacting hand pose estimation from a single RGB image is a challenging task, due to serious self-occlusion and inter-occlusion towards hands, confusing similar appearance patterns between 2 hands, ill-posed joint position mapping from 2D to 3D, etc.. To address these, we propose to extend A2J-the state-of-the-art depth-based 3D single hand pose estimation method-to RGB domain under interacting hand condition. Our key idea is to equip A2J with strong local-global aware ability to well capture interacting hands' local fine details and global articulated clues among joints jointly. To this end, A2J is evolved under Transformer's non-local encoding-decoding framework to build A2J-Transformer. It holds 3 main advantages over A2J. First, self-attention across local anchor points is built to make them global spatial context aware to better capture joints' articulation clues for resisting occlusion. Secondly, each anchor point is regarded as learnable query with adaptive feature learning for facilitating pattern fitting capacity, instead of having the same local representation with the others. Last but not least, anchor point locates in 3D space instead of 2D as in A2J, to leverage 3D pose prediction. Experiments on challenging InterHand 2.6M demonstrate that, A2J-Transformer can achieve state-of-the-art model-free performance (3.38mm MPJPE advancement in 2-hand case) and can also be applied to depth domain with strong generalization.

cs.CV↗

arXiv2022

TTS-Guided Training for Accent Conversion Without Parallel Data

Accent Conversion (AC) seeks to change the accent of speech from one (source) to another (target) while preserving the speech content and speaker identity. However, many AC approaches rely on source-target parallel speech data. We propose a novel accent conversion framework without the need of parallel data. Specifically, a text-to-speech (TTS) system is first pretrained with target-accented speech data. This TTS model and its hidden representations are expected to be associated only with the target accent. Then, a speech encoder is trained to convert the accent of the speech under the supervision of the pretrained TTS model. In doing so, the source-accented speech and its corresponding transcription are forwarded to the speech encoder and the pretrained TTS, respectively. The output of the speech encoder is optimized to be the same as the text embedding in the TTS system. At run-time, the speech encoder is combined with the pretrained TTS decoder to convert the source-accented speech toward the target. In the experiments, we converted English with two source accents (Chinese and Indian) to the target accent (American/British/Canadian). Both objective metrics and subjective listening tests successfully validate that, without any parallel data, the proposed approach generates speech samples that are close to the target accent with high speech quality.

eess.AS↗

arXiv2022

Bayesian Layer Graph Convolutioanl Network for Hyperspetral Image Classification

In recent years, research on hyperspectral image (HSI) classification has continuous progress on introducing deep network models, and recently the graph convolutional network (GCN) based models have shown impressive performance. However, these deep learning frameworks based on point estimation suffer from low generalization and inability to quantify the classification results uncertainty. On the other hand, simply applying the Bayesian Neural Network (BNN) based on distribution estimation to classify the HSI is unable to achieve high classification accuracy due to the large amount of parameters. In this paper, we design a Bayesian layer with Bayesian idea as an insertion layer into point estimation based neural networks, and propose a Bayesian Layer Graph Convolutional Network (BLGCN) model by combining graph convolution operations, which can effectively extract graph information and estimate the uncertainty of classification results. Moreover, a Generative Adversarial Network (GAN) is built to solve the sample imbalance problem of HSI dataset. Finally, we design a dynamic control training strategy based on the confidence interval of the classification results, which will terminate the training early when the confidence interval reaches the preseted threshold. The experimental results show that our model achieves a balance between high classification accuracy and strong generalization. In addition, it can quantifies the uncertainty of the classification results.

cs.CV↗

arXiv2022

Towards Consistency and Complementarity: A Multiview Graph Information Bottleneck Approach

The empirical studies of Graph Neural Networks (GNNs) broadly take the original node feature and adjacency relationship as singleview input, ignoring the rich information of multiple graph views. To circumvent this issue, the multiview graph analysis framework has been developed to fuse graph information across views. How to model and integrate shared (i.e. consistency) and view-specific (i.e. complementarity) information is a key issue in multiview graph analysis. In this paper, we propose a novel Multiview Variational Graph Information Bottleneck (MVGIB) principle to maximize the agreement for common representations and the disagreement for view-specific representations. Under this principle, we formulate the common and view-specific information bottleneck objectives across multiviews by using constraints from mutual information. However, these objectives are hard to directly optimize since the mutual information is computationally intractable. To tackle this challenge, we derive variational lower and upper bounds of mutual information terms, and then instead optimize variational bounds to find the approximate solutions for the information objectives. Extensive experiments on graph benchmark datasets demonstrate the superior effectiveness of the proposed method.

cs.LG↗

arXiv2022

Efficient Re-parameterization Operations Search for Easy-to-Deploy Network Based on Directional Evolutionary Strategy

Structural re-parameterization (Rep) methods has achieved significant performance improvement on traditional convolutional network. Most current Rep methods rely on prior knowledge to select the reparameterization operations. However, the performance of architecture is limited by the type of operations and prior knowledge. To break this restriction, in this work, an improved re-parameterization search space is designed, which including more type of re-parameterization operations. Concretely, the performance of convolutional networks can be further improved by the search space. To effectively explore this search space, an automatic re-parameterization enhancement strategy is designed based on neural architecture search (NAS), which can search a excellent re-parameterization architecture. Besides, we visualize the output features of the architecture to analyze the reasons for the formation of the re-parameterization architecture. On public datasets, we achieve better results. Under the same training conditions as ResNet, we improve the accuracy of ResNet-50 by 1.82% on ImageNet-1k.

cs.AI↗

arXiv2022

RepNAS: Searching for Efficient Re-parameterizing Blocks

In the past years, significant improvements in the field of neural architecture search(NAS) have been made. However, it is still challenging to search for efficient networks due to the gap between the searched constraint and real inference time exists. To search for a high-performance network with low inference time, several previous works set a computational complexity constraint for the search algorithm. However, many factors affect the speed of inference(e.g., FLOPs, MACs). The correlation between a single indicator and the latency is not strong. Currently, some re-parameterization(Rep) techniques are proposed to convert multi-branch to single-path architecture which is inference-friendly. Nevertheless, multi-branch architectures are still human-defined and inefficient. In this work, we propose a new search space that is suitable for structural re-parameterization techniques. RepNAS, a one-stage NAS approach, is present to efficiently search the optimal diverse branch block(ODBB) for each layer under the branch number constraint. Our experimental results show the searched ODBB can easily surpass the manual diverse branch block(DBB) with efficient training.

cs.LG↗

arXiv2022

Real transmission and reflection zeros of periodic structures with a bound state in the continuum

For lossless periodic structures with a proper symmetry, the transmission and reflection spectra often have peaks and dips that are truly $100\%$ and $0\%$, respectively. The full peaks and zero dips typically appear near resonant frequencies, and they are robust with respect to structural perturbations that preserve the required symmetry. However, current theories on the existence of full peaks and zero dips are incomplete and difficult to use. For periodic structures with a bound state in the continuum (BIC), we present a new theory on the existence of real transmission and reflection zeros that correspond to the zero dips in the transmission and reflection spectra. Our theory is relatively simple, complete, and easy to use. Numerical examples are presented to validate the new theory.

physics.optics↗

arXiv2022

VisualTTS: TTS with Accurate Lip-Speech Synchronization for Automatic Voice Over

In this paper, we formulate a novel task to synthesize speech in sync with a silent pre-recorded video, denoted as automatic voice over (AVO). Unlike traditional speech synthesis, AVO seeks to generate not only human-sounding speech, but also perfect lip-speech synchronization. A natural solution to AVO is to condition the speech rendering on the temporal progression of lip sequence in the video. We propose a novel text-to-speech model that is conditioned on visual input, named VisualTTS, for accurate lip-speech synchronization. The proposed VisualTTS adopts two novel mechanisms that are 1) textual-visual attention, and 2) visual fusion strategy during acoustic decoding, which both contribute to forming accurate alignment between the input text content and lip motion in input lip sequence. Experimental results show that VisualTTS achieves accurate lip-speech synchronization and outperforms all baseline systems.

eess.AS↗

arXiv2022

Out-of-Domain Semantics to the Rescue! Zero-Shot Hybrid Retrieval Models

The pre-trained language model (eg, BERT) based deep retrieval models achieved superior performance over lexical retrieval models (eg, BM25) in many passage retrieval tasks. However, limited work has been done to generalize a deep retrieval model to other tasks and domains. In this work, we carefully select five datasets, including two in-domain datasets and three out-of-domain datasets with different levels of domain shift, and study the generalization of a deep model in a zero-shot setting. Our findings show that the performance of a deep retrieval model is significantly deteriorated when the target domain is very different from the source domain that the model was trained on. On the contrary, lexical models are more robust across domains. We thus propose a simple yet effective framework to integrate lexical and deep retrieval models. Our experiments demonstrate that these two models are complementary, even when the deep model is weaker in the out-of-domain setting. The hybrid model obtains an average of 20.4% relative gain over the deep retrieval model, and an average of 9.54% over the lexical model in three out-of-domain datasets.

cs.IR↗

arXiv2021

Gemini: Practical Reconfigurable Datacenter Networks with Topology and Traffic Engineering

To reduce cost, datacenter network operators are exploring blocking network designs. An example of such a design is a "spine-free" form of a Fat-Tree, in which pods directly connect to each other, rather than via spine blocks. To maintain application-perceived performance in the face of dynamic workloads, these new designs must be able to reconfigure routing and the inter-pod topology. Gemini is a system designed to achieve these goals on commodity hardware while reconfiguring the network infrequently, rendering these blocking designs practical enough for deployment in the near future. The key to Gemini is the joint optimization of topology and routing, using as input a robust estimation of future traffic derived from multiple historical traffic matrices. Gemini "hedges" against unpredicted bursts, by spreading these bursts across multiple paths, to minimize packet loss in exchange for a small increase in path lengths. It incorporates a robust decision algorithm to determine when to reconfigure, and whether to use hedging. Data from tens of production fabrics allows us to categorize these as either low-or high-volatility; these categories seem stable. For the former, Gemini finds topologies and routing with near-optimal performance and cost. For the latter, Gemini's use of multi-traffic-matrix optimization and hedging avoids the need for frequent topology reconfiguration, with only marginal increases in path length. As a result, Gemini can support existing workloads on these production fabrics using a spine-free topology that is half the cost of the existing topology on these fabrics.

cs.NI↗

arXiv2021

DeepA: A Deep Neural Analyzer For Speech And Singing Vocoding

Conventional vocoders are commonly used as analysis tools to provide interpretable features for downstream tasks such as speech synthesis and voice conversion. They are built under certain assumptions about the signals following signal processing principle, therefore, not easily generalizable to different audio, for example, from speech to singing. In this paper, we propose a deep neural analyzer, denoted as DeepA - a neural vocoder that extracts F0 and timbre/aperiodicity encoding from the input speech that emulate those defined in conventional vocoders. Therefore, the resulting parameters are more interpretable than other latent neural representations. At the same time, as the deep neural analyzer is learnable, it is expected to be more accurate for signal reconstruction and manipulation, and generalizable from speech to singing. The proposed neural analyzer is built based on a variational autoencoder (VAE) architecture. We show that DeepA improves F0 estimation over the conventional vocoder (WORLD). To our best knowledge, this is the first study dedicated to the development of a neural framework for extracting learnable vocoder-like parameters.

eess.AS↗