arXiv subjects

Yitong Li

Publications and source records attributed to Yitong Li.

At least 127 records · Page 7Linked to original sources

arXiv2021

Polarized hyperspectral imaging with single fiber bundle via incoherent light transmission matrix approach

The scattering of multispectral incoherent light is a common and unfavorable signal scrambling in natural scenes. However, the blurred light spot due to scattering still holds lots of information remaining to be explored. Former methods failed to recover the polarized hyperspectral information from scattered incoherent light or relied on additional dispersion elements. Here we put forward the transmission matrix (TM) approach for extended objects under incoherent illumination by speculating the unknown TM through experimentally calibrated or digitally emulated ways. Employing a fiber bundle as a powerful imaging and dispersion element, we recover the spatial information in 252 polarized-spectral channels from a single speckle, thus achieving single-shot, high-resolution, broadband hyperspectral imaging for two polarization states with the cheap, compact, fiber-bundle-only system. Based on the scattering principle itself, our method not only greatly improves the robustness of the TM approach to retrieve the input spectral information, but also reveals the feasibility to explore the polarized spatio-spectral information from blurry speckles only with the help of simple optical setups.

eess.IV↗

arXiv2020

Differentially Private Representation for NLP: Formal Guarantee and An Empirical Study on Privacy and Fairness

It has been demonstrated that hidden representation learned by a deep model can encode private information of the input, hence can be exploited to recover such information with reasonable accuracy. To address this issue, we propose a novel approach called Differentially Private Neural Representation (DPNR) to preserve the privacy of the extracted representation from text. DPNR utilises Differential Privacy (DP) to provide a formal privacy guarantee. Further, we show that masking words via dropout can further enhance privacy. To maintain utility of the learned representation, we integrate DP-noisy representation into a robust training process to derive a robust target model, which also helps for model fairness over various demographic variables. Experimental results on benchmark datasets under various parameter settings demonstrate that DPNR largely reduces privacy leakage without significantly sacrificing the main task performance.

cs.LG↗

arXiv2020

Sequential Attention GAN for Interactive Image Editing

Most existing text-to-image synthesis tasks are static single-turn generation, based on pre-defined textual descriptions of images. To explore more practical and interactive real-life applications, we introduce a new task - Interactive Image Editing, where users can guide an agent to edit images via multi-turn textual commands on-the-fly. In each session, the agent takes a natural language description from the user as the input and modifies the image generated in the previous turn to a new design, following the user description. The main challenges in this sequential and interactive image generation task are two-fold: 1) contextual consistency between a generated image and the provided textual description; 2) step-by-step region-level modification to maintain visual consistency across the generated image sequence in each session. To address these challenges, we propose a novel Sequential Attention Generative Adversarial Net-work (SeqAttnGAN), which applies a neural state tracker to encode the previous image and the textual description in each turn of the sequence, and uses a GAN framework to generate a modified version of the image that is consistent with the preceding images and coherent with the description. To achieve better region-specific refinement, we also introduce a sequential attention mechanism into the model. To benchmark on the new task, we introduce two new datasets, Zap-Seq and DeepFashion-Seq, which contain multi-turn sessions with image-description sequences in the fashion domain. Experiments on both datasets show that the proposed SeqAttnGANmodel outperforms state-of-the-art approaches on the interactive image editing task across all evaluation metrics including visual quality, image sequence coherence, and text-image consistency.

cs.CV↗

arXiv2020

How to Democratise and Protect AI: Fair and Differentially Private Decentralised Deep Learning

This paper firstly considers the research problem of fairness in collaborative deep learning, while ensuring privacy. A novel reputation system is proposed through digital tokens and local credibility to ensure fairness, in combination with differential privacy to guarantee privacy. In particular, we build a fair and differentially private decentralised deep learning framework called FDPDDL, which enables parties to derive more accurate local models in a fair and private manner by using our developed two-stage scheme: during the initialisation stage, artificial samples generated by Differentially Private Generative Adversarial Network (DPGAN) are used to mutually benchmark the local credibility of each party and generate initial tokens; during the update stage, Differentially Private SGD (DPSGD) is used to facilitate collaborative privacy-preserving deep learning, and local credibility and tokens of each party are updated according to the quality and quantity of individually released gradients. Experimental results on benchmark datasets under three realistic settings demonstrate that FDPDDL achieves high fairness, yields comparable accuracy to the centralised and distributed frameworks, and delivers better accuracy than the standalone framework.

cs.CR↗

arXiv2020

Understanding the Dynamics of Information Flow During Disaster Response Using Absorbing Markov Chains

This paper aims to derive a quantitative model to evaluate the impact of information flow on the effectiveness of disaster response. At the core of the model is a specialized absorbing Markov chain that models the process of delivering federal assistance to the community while considering stakeholder interactions and information flow uncertainty. Using the proposed model, the probability of community satisfaction is computed to reflect the effectiveness of disaster response. A hypothetical example is provided to demonstrate the applicability and interpretability of the derived quantitative model. Practically, the research provides governmental stakeholders interpretable insights for evaluating the impact of information flow on their disaster response effectiveness so that critical stakeholders can be targeted proactive actions for enhanced disaster response.

cs.SI↗

arXiv2020

Automated Abstraction of Operation Processes from Unstructured Text for Simulation Modeling

Abstraction of operation processes is a fundamental step for simulation modeling. To reliably abstract an operation process, modelers rely on text information to study and understand details of operations. Aiming at reducing modelers' interpretation load and ensuring the reliability of the abstracted information, this research proposes a systematic methodology to automate the abstraction of operation processes. The methodology applies rule-based information extraction to automatically extract operation process-related information from unstructured text and creates graphical representations of operation processes using the extracted information. To demonstrate the applicability and feasibility of the proposed methodology, a text description of an earthmoving operation is used to create its corresponding graphical representation. Overall, this research enhances the state-of-the-art simulation modeling through achieving automated abstraction of operation processes, which largely reduces modelers' interpretation load and ensures the reliability of the abstracted operation processes.

cs.IR↗

arXiv2020

Towards Differentially Private Text Representations

Most deep learning frameworks require users to pool their local data or model updates to a trusted server to train or maintain a global model. The assumption of a trusted server who has access to user information is ill-suited in many applications. To tackle this problem, we develop a new deep learning framework under an untrusted server setting, which includes three modules: (1) embedding module, (2) randomization module, and (3) classifier module. For the randomization module, we propose a novel local differentially private (LDP) protocol to reduce the impact of privacy parameter $ε$ on accuracy, and provide enhanced flexibility in choosing randomization probabilities for LDP. Analysis and experiments show that our framework delivers comparable or even better performance than the non-private framework and existing LDP protocols, demonstrating the advantages of our LDP protocol.

cs.LG↗

arXiv2020

Impedance-Based Whole-System Modeling for a Composite Grid via Frame-Dynamics Embedding

The paper establishes a methodology to overcome the difficulty of dynamic frame alignment and system separation in impedance modeling of ac grids, and thereby enables impedance-based whole-system modeling of generator-converter composite power systems. The methodology is based on a frame-dynamics-embedding transformation via an intermediary steady frame between local and global frames, which yields a locally defined impedance model for each generator or converter that does not rely on a global frame but retains all frame dynamics. The individual impedance model can then be readily combined into a whole-system model even for meshed networks via the proposed closed-loop formulation without network separation. Compared to start-of-the-art impedance-based models, the proposed method retains both frame dynamics and scalability, and is generally applicable to various network topologies (meshed, radial, etc) and combinations of machines (generators, motors, converters, etc). The methodology is used to analyze the dynamic interaction between generators and converters in a composite grid, which yields important findings and potential solutions for unstable oscillation caused by PLL-swing coupling in low-inertia grids.

eess.SY↗

arXiv2020

Towards Fair and Privacy-Preserving Federated Deep Models

The current standalone deep learning framework tends to result in overfitting and low utility. This problem can be addressed by either a centralized framework that deploys a central server to train a global model on the joint data from all parties, or a distributed framework that leverages a parameter server to aggregate local model updates. Server-based solutions are prone to the problem of a single-point-of-failure. In this respect, collaborative learning frameworks, such as federated learning (FL), are more robust. Existing federated learning frameworks overlook an important aspect of participation: fairness. All parties are given the same final model without regard to their contributions. To address these issues, we propose a decentralized Fair and Privacy-Preserving Deep Learning (FPPDL) framework to incorporate fairness into federated deep learning models. In particular, we design a local credibility mutual evaluation mechanism to guarantee fairness, and a three-layer onion-style encryption scheme to guarantee both accuracy and privacy. Different from existing FL paradigm, under FPPDL, each participant receives a different version of the FL model with performance commensurate with his contributions. Experiments on benchmark datasets demonstrate that FPPDL balances fairness, privacy and accuracy. It enables federated learning ecosystems to detect and isolate low-contribution parties, thereby promoting responsible participation.

cs.CR↗

arXiv2020

Toward Interpretability of Dual-Encoder Models for Dialogue Response Suggestions

This work shows how to improve and interpret the commonly used dual encoder model for response suggestion in dialogue. We present an attentive dual encoder model that includes an attention mechanism on top of the extracted word-level features from two encoders, one for context and one for label respectively. To improve the interpretability in the dual encoder models, we design a novel regularization loss to minimize the mutual information between unimportant words and desired labels, in addition to the original attention method, so that important words are emphasized while unimportant words are de-emphasized. This can help not only with model interpretability, but can also further improve model accuracy. We propose an approximation method that uses a neural network to calculate the mutual information. Furthermore, by adding a residual layer between raw word embeddings and the final encoded context feature, word-level interpretability is preserved at the final prediction of the model. We compare the proposed model with existing methods for the dialogue response task on two public datasets (Persona and Ubuntu). The experiments demonstrate the effectiveness of the proposed model in terms of better Recall@1 accuracy and visualized interpretability.

cs.CL↗

arXiv2019

Dynamic Embedding on Textual Networks via a Gaussian Process

Textual network embedding aims to learn low-dimensional representations of text-annotated nodes in a graph. Prior work in this area has typically focused on fixed graph structures; however, real-world networks are often dynamic. We address this challenge with a novel end-to-end node-embedding model, called Dynamic Embedding for Textual Networks with a Gaussian Process (DetGP). After training, DetGP can be applied efficiently to dynamic graphs without re-training or backpropagation. The learned representation of each node is a combination of textual and structural embeddings. Because the structure is allowed to be dynamic, our method uses the Gaussian process to take advantage of its non-parametric properties. To use both local and global graph structures, diffusion is used to model multiple hops between neighbors. The relative importance of global versus local structure for the embeddings is learned automatically. With the non-parametric nature of the Gaussian process, updating the embeddings for a changed graph structure requires only a forward pass through the learned model. Considering link prediction and node classification, experiments demonstrate the empirical effectiveness of our method compared to baseline approaches. We further show that DetGP can be straightforwardly and efficiently applied to dynamic textual networks.

cs.LG↗

arXiv2019

Kernel-Based Approaches for Sequence Modeling: Connections to Neural Methods

We investigate time-dependent data analysis from the perspective of recurrent kernel machines, from which models with hidden units and gated memory cells arise naturally. By considering dynamic gating of the memory cell, a model closely related to the long short-term memory (LSTM) recurrent neural network is derived. Extending this setup to $n$-gram filters, the convolutional neural network (CNN), Gated CNN, and recurrent additive network (RAN) are also recovered as special cases. Our analysis provides a new perspective on the LSTM, while also extending it to $n$-gram convolutional filters. Experiments are performed on natural language processing tasks and on analysis of local field potentials (neuroscience). We demonstrate that the variants we derive from kernels perform on par or even better than traditional neural methods. For the neuroscience application, the new models demonstrate significant improvements relative to the prior state of the art.

stat.ML↗

arXiv2019

LMVP: Video Predictor with Leaked Motion Information

We propose a Leaked Motion Video Predictor (LMVP) to predict future frames by capturing the spatial and temporal dependencies from given inputs. The motion is modeled by a newly proposed component, motion guider, which plays the role of both learner and teacher. Specifically, it {\em learns} the temporal features from real data and {\em guides} the generator to predict future frames. The spatial consistency in video is modeled by an adaptive filtering network. To further ensure the spatio-temporal consistency of the prediction, a discriminator is also adopted to distinguish the real and generated frames. Further, the discriminator leaks information to the motion guider and the generator to help the learning of motion. The proposed LMVP can effectively learn the static and temporal features in videos without the need for human labeling. Experiments on synthetic and real data demonstrate that LMVP can yield state-of-the-art results.

cs.CV↗

arXiv2019

Enhanced Input Modeling for Construction Simulation using Bayesian Deep Neural Networks

This paper aims to propose a novel deep learning-integrated framework for deriving reliable simulation input models through incorporating multi-source information. The framework sources and extracts multisource data generated from construction operations, which provides rich information for input modeling. The framework implements Bayesian deep neural networks to facilitate the purpose of incorporating richer information in input modeling. A case study on road paving operation is performed to test the feasibility and applicability of the proposed framework. Overall, this research enhances input modeling by deriving detailed input models, thereby, augmenting the decision-making processes in construction operations. This research also sheds lights on prompting data-driven simulation through incorporating machine learning techniques.

cs.LG↗

arXiv2019

Semi-supervised Stochastic Multi-Domain Learning using Variational Inference

Supervised models of NLP rely on large collections of text which closely resemble the intended testing setting. Unfortunately matching text is often not available in sufficient quantity, and moreover, within any domain of text, data is often highly heterogenous. In this paper we propose a method to distill the important domain signal as part of a multi-domain learning system, using a latent variable model in which parts of a neural model are stochastically gated based on the inferred domain. We compare the use of discrete versus continuous latent variables, operating in a domain-supervised or a domain semi-supervised setting, where the domain is known only for a subset of training inputs. We show that our model leads to substantial performance improvements over competitive benchmark domain adaptation methods, including methods using adversarial learning.

cs.CL↗

arXiv2019

Interpreting Frame Transformations as Diagonalization of Harmonic Transfer Functions

Analysis of ac electrical systems can be performed via frame transformations in the time-domain or via harmonic transfer functions (HTFs) in the frequency-domain. The two approaches each have unique advantages but are hard to reconcile because the coupling effect in the frequency-domain leads to infinite dimensional HTF matrices that need to be truncated. This paper explores the relation between the two representations and shows that applying a similarity transformation to an HTF matrix creates a direct equivalence to a frame transformation on the input-output signals. Under certain conditions, such similarity transformations have a diagonalizing effect which, essentially, reduces the HTF matrix order from infinity to two or one, making the matrix tractable mathematically without truncation or approximation. This theory is applied to a droop-controlled voltage source inverter as an illustrative example. A stability criterion is derived in the frequency-domain which agrees with the conventional state-space model but offers greater insights into the mechanism of instability in terms of the negative damping (non-passivity) under droop control. The paper not only establishes a unified view in theory but also offers an effective practical tool for stability assessment.

eess.SP↗

arXiv2019

StoryGAN: A Sequential Conditional GAN for Story Visualization

We propose a new task, called Story Visualization. Given a multi-sentence paragraph, the story is visualized by generating a sequence of images, one for each sentence. In contrast to video generation, story visualization focuses less on the continuity in generated images (frames), but more on the global consistency across dynamic scenes and characters -- a challenge that has not been addressed by any single-image or video generation methods. We therefore propose a new story-to-image-sequence generation model, StoryGAN, based on the sequential conditional GAN framework. Our model is unique in that it consists of a deep Context Encoder that dynamically tracks the story flow, and two discriminators at the story and image levels, to enhance the image quality and the consistency of the generated sequences. To evaluate the model, we modified existing datasets to create the CLEVR-SV and Pororo-SV datasets. Empirically, StoryGAN outperforms state-of-the-art models in image quality, contextual consistency metrics, and human evaluation.

cs.CV↗

arXiv2019

On Target Shift in Adversarial Domain Adaptation

Discrepancy between training and testing domains is a fundamental problem in the generalization of machine learning techniques. Recently, several approaches have been proposed to learn domain invariant feature representations through adversarial deep learning. However, label shift, where the percentage of data in each class is different between domains, has received less attention. Label shift naturally arises in many contexts, especially in behavioral studies where the behaviors are freely chosen. In this work, we propose a method called Domain Adversarial nets for Target Shift (DATS) to address label shift while learning a domain invariant representation. This is accomplished by using distribution matching to estimate label proportions in a blind test set. We extend this framework to handle multiple domains by developing a scheme to upweight source domains most similar to the target domain. Empirical results show that this framework performs well under large label shift in synthetic and real experiments, demonstrating the practical importance.

stat.ML↗