arXiv subjects

Liu Yang

Publications and source records attributed to Liu Yang.

At least 181 records · Page 10Linked to original sources

arXiv2021

Learning Functional Priors and Posteriors from Data and Physics

We develop a new Bayesian framework based on deep neural networks to be able to extrapolate in space-time using historical data and to quantify uncertainties arising from both noisy and gappy data in physical problems. Specifically, the proposed approach has two stages: (1) prior learning and (2) posterior estimation. At the first stage, we employ the physics-informed Generative Adversarial Networks (PI-GAN) to learn a functional prior either from a prescribed function distribution, e.g., Gaussian process, or from historical data and physics. At the second stage, we employ the Hamiltonian Monte Carlo (HMC) method to estimate the posterior in the latent space of PI-GANs. In addition, we use two different approaches to encode the physics: (1) automatic differentiation, used in the physics-informed neural networks (PINNs) for scenarios with explicitly known partial differential equations (PDEs), and (2) operator regression using the deep operator network (DeepONet) for PDE-agnostic scenarios. We then test the proposed method for (1) meta-learning for one-dimensional regression, and forward/inverse PDE problems (combined with PINNs); (2) PDE-agnostic physical problems (combined with DeepONet), e.g., fractional diffusion as well as saturated stochastic (100-dimensional) flows in heterogeneous porous media; and (3) spatial-temporal regression problems, i.e., inference of a marine riser displacement field. The results demonstrate that the proposed approach can provide accurate predictions as well as uncertainty quantification given very limited scattered and noisy data, since historical data could be available to provide informative priors. In summary, the proposed method is capable of learning flexible functional priors, and can be extended to big data problems using stochastic HMC or normalizing flows since the latent space is generally characterized as low dimensional.

cs.LG↗

arXiv2021

Passage Retrieval for Outside-Knowledge Visual Question Answering

In this work, we address multi-modal information needs that contain text questions and images by focusing on passage retrieval for outside-knowledge visual question answering. This task requires access to outside knowledge, which in our case we define to be a large unstructured passage collection. We first conduct sparse retrieval with BM25 and study expanding the question with object names and image captions. We verify that visual clues play an important role and captions tend to be more informative than object names in sparse retrieval. We then construct a dual-encoder dense retriever, with the query encoder being LXMERT, a multi-modal pre-trained transformer. We further show that dense retrieval significantly outperforms sparse retrieval that uses object expansion. Moreover, dense retrieval matches the performance of sparse retrieval that leverages human-generated captions.

cs.IR↗

arXiv2021

Generative Ensemble Regression: Learning Particle Dynamics from Observations of Ensembles with Physics-Informed Deep Generative Models

We propose a new method for inferring the governing stochastic ordinary differential equations (SODEs) by observing particle ensembles at discrete and sparse time instants, i.e., multiple "snapshots". Particle coordinates at a single time instant, possibly noisy or truncated, are recorded in each snapshot but are unpaired across the snapshots. By training a physics-informed generative model that generates "fake" sample paths, we aim to fit the observed particle ensemble distributions with a curve in the probability measure space, which is induced from the inferred particle dynamics. We employ different metrics to quantify the differences between distributions, e.g., the sliced Wasserstein distances and the adversarial losses in generative adversarial networks (GANs). We refer to this method as generative "ensemble-regression" (GER), in analogy to the classic "point-regression", where we infer the dynamics by performing regression in the Euclidean space. We illustrate the GER by learning the drift and diffusion terms of particle ensembles governed by SODEs with Brownian motions and Levy processes up to 100 dimensions. We also discuss how to treat cases with noisy or truncated observations. Apart from systems consisting of independent particles, we also tackle nonlocal interacting particle systems with unknown interaction potential parameters by constructing a physics-informed loss function. Finally, we investigate scenarios of paired observations and discuss how to reduce the dimensionality in such cases by proving a convergence theorem that provides theoretical support.

cs.LG↗

arXiv2021

Weakly-Supervised Open-Retrieval Conversational Question Answering

Recent studies on Question Answering (QA) and Conversational QA (ConvQA) emphasize the role of retrieval: a system first retrieves evidence from a large collection and then extracts answers. This open-retrieval ConvQA setting typically assumes that each question is answerable by a single span of text within a particular passage (a span answer). The supervision signal is thus derived from whether or not the system can recover an exact match of this ground-truth answer span from the retrieved passages. This method is referred to as span-match weak supervision. However, information-seeking conversations are challenging for this span-match method since long answers, especially freeform answers, are not necessarily strict spans of any passage. Therefore, we introduce a learned weak supervision approach that can identify a paraphrased span of the known answer in a passage. Our experiments on QuAC and CoQA datasets show that the span-match weak supervisor can only handle conversations with span answers, and has less satisfactory results for freeform answers generated by people. Our method is more flexible as it can handle both span answers and freeform answers. Moreover, our method can be more powerful when combined with the span-match method which shows it is complementary to the span-match method. We also conduct in-depth analyses to show more insights on open-retrieval ConvQA under a weak supervision setting.

cs.IR↗

arXiv2021

Flow-based Generative Models for Learning Manifold to Manifold Mappings

Many measurements or observations in computer vision and machine learning manifest as non-Euclidean data. While recent proposals (like spherical CNN) have extended a number of deep neural network architectures to manifold-valued data, and this has often provided strong improvements in performance, the literature on generative models for manifold data is quite sparse. Partly due to this gap, there are also no modality transfer/translation models for manifold-valued data whereas numerous such methods based on generative models are available for natural images. This paper addresses this gap, motivated by a need in brain imaging -- in doing so, we expand the operating range of certain generative models (as well as generative models for modality transfer) from natural images to images with manifold-valued measurements. Our main result is the design of a two-stream version of GLOW (flow-based invertible generative models) that can synthesize information of a field of one type of manifold-valued measurements given another. On the theoretical side, we introduce three kinds of invertible layers for manifold-valued data, which are not only analogous to their functionality in flow-based generative models (e.g., GLOW) but also preserve the key benefits (determinants of the Jacobian are easy to calculate). For experiments, on a large dataset from the Human Connectome Project (HCP), we show promising results where we can reliably and accurately reconstruct brain images of a field of orientation distribution functions (ODF) from diffusion tensor images (DTI), where the latter has a $5\times$ faster acquisition time but at the expense of worse angular resolution.

cs.CV↗

arXiv2021

Robust propagation of internal coastal Kelvin waves in complex domains

We experimentally investigate internal coastal Kelvin waves in a two-layer fluid system on a rotating table. Waves in our system propagate in the prograde direction and are exponentially localized near the boundary. Our experiments verify the theoretical dispersion relation of the wave and show that the wave amplitude decays exponentially along the propagation direction. We further demonstrate that the waves can robustly propagate along boundaries of complex geometries without being scattered and that adding obstacles to the wave propagation path does not cause additional attenuation.

physics.flu-dyn↗

arXiv2021

Measure-conditional Discriminator with Stationary Optimum for GANs and Statistical Distance Surrogates

We propose a simple but effective modification of the discriminators, namely measure-conditional discriminators, as a plug-and-play module for different GANs. By taking the generated distributions as part of input so that the target optimum for the discriminator is stationary, the proposed discriminator is more robust than the vanilla one. A variant of the measure-conditional discriminator can also handle multiple target distributions, or act as a surrogate model of statistical distances such as KL divergence with applications to transfer learning.

cs.LG↗

arXiv2020

Long Range Arena: A Benchmark for Efficient Transformers

Transformers do not scale very well to long sequence lengths largely because of quadratic self-attention complexity. In the recent months, a wide spectrum of efficient, fast Transformers have been proposed to tackle this problem, more often than not claiming superior or comparable model quality to vanilla Transformer models. To this date, there is no well-established consensus on how to evaluate this class of models. Moreover, inconsistent benchmarking on a wide spectrum of tasks and datasets makes it difficult to assess relative model quality amongst many models. This paper proposes a systematic and unified benchmark, LRA, specifically focused on evaluating model quality under long-context scenarios. Our benchmark is a suite of tasks consisting of sequences ranging from $1K$ to $16K$ tokens, encompassing a wide range of data types and modalities such as text, natural, synthetic images, and mathematical expressions requiring similarity, structural, and visual-spatial reasoning. We systematically evaluate ten well-established long-range Transformer models (Reformers, Linformers, Linear Transformers, Sinkhorn Transformers, Performers, Synthesizers, Sparse Transformers, and Longformers) on our newly proposed benchmark suite. LRA paves the way towards better understanding this class of efficient Transformer models, facilitates more research in this direction, and presents new challenging tasks to tackle. Our benchmark code will be released at https://github.com/google-research/long-range-arena.

cs.LG↗

arXiv2020

Beyond 512 Tokens: Siamese Multi-depth Transformer-based Hierarchical Encoder for Long-Form Document Matching

Many natural language processing and information retrieval problems can be formalized as the task of semantic matching. Existing work in this area has been largely focused on matching between short texts (e.g., question answering), or between a short and a long text (e.g., ad-hoc retrieval). Semantic matching between long-form documents, which has many important applications like news recommendation, related article recommendation and document clustering, is relatively less explored and needs more research effort. In recent years, self-attention based models like Transformers and BERT have achieved state-of-the-art performance in the task of text matching. These models, however, are still limited to short text like a few sentences or one paragraph due to the quadratic computational complexity of self-attention with respect to input text length. In this paper, we address the issue by proposing the Siamese Multi-depth Transformer-based Hierarchical (SMITH) Encoder for long-form document matching. Our model contains several innovations to adapt self-attention models for longer text input. In order to better capture sentence level semantic relations within a document, we pre-train the model with a novel masked sentence block language modeling task in addition to the masked word language modeling task used by BERT. Our experimental results on several benchmark datasets for long-form document matching show that our proposed SMITH model outperforms the previous state-of-the-art models including hierarchical attention, multi-depth attention-based hierarchical recurrent neural network, and BERT. Comparing to BERT based baselines, our model is able to increase maximum input text length from 512 to 2048. We will open source a Wikipedia based benchmark dataset, code and a pre-trained checkpoint to accelerate future research on long-form document matching.

cs.IR↗

arXiv2020

Dimensional crossover in spin Hall oscillators

Auto-oscillations of magnetization driven by direct spin current have been previously observed in multiple quasi-zero-dimensional (0D) ferromagnetic systems such as nanomagnets and nanocontacts. Recently, it was shown that pure spin Hall current can excite coherent auto-oscillatory dynamics in quasi-one-dimensional (1D) ferromagnetic nanowires but not in quasi-two-dimensional (2D) ferromagnetic films. Here we study the 1D to 2D dimensional crossover of current-driven magnetization dynamics in wire-based Pt/$\mathrm{Ni}_{80}\mathrm{Fe}_{20}$ bilayer spin Hall oscillators via varying the wire width. We find that increasing the wire width results in an increase of the number of excited auto-oscillatory modes accompanied by a decrease of the amplitude and coherence of each mode. We also observe a crossover from a hard to a soft onset of the auto-oscillations with increasing the wire width. The amplitude of auto-oscillations rapidly decreases with increasing temperature suggesting that interactions of the phase-coherent auto-oscillatory modes with incoherent thermal magnons plays an important role in suppression of the auto-oscillatory dynamics. Our measurements set the upper limit on the dimensions of an individual spin Hall oscillator and elucidate the mechanisms leading to suppression of coherent auto-oscillations with increasing oscillator size.

cond-mat.mes-hall↗

arXiv2020

DiPair: Fast and Accurate Distillation for Trillion-Scale Text Matching and Pair Modeling

Pre-trained models like BERT (Devlin et al., 2018) have dominated NLP / IR applications such as single sentence classification, text pair classification, and question answering. However, deploying these models in real systems is highly non-trivial due to their exorbitant computational costs. A common remedy to this is knowledge distillation (Hinton et al., 2015), leading to faster inference. However -- as we show here -- existing works are not optimized for dealing with pairs (or tuples) of texts. Consequently, they are either not scalable or demonstrate subpar performance. In this work, we propose DiPair -- a novel framework for distilling fast and accurate models on text pair tasks. Coupled with an end-to-end training strategy, DiPair is both highly scalable and offers improved quality-speed tradeoffs. Empirical studies conducted on both academic and real-world e-commerce benchmarks demonstrate the efficacy of the proposed approach with speedups of over 350x and minimal quality drop relative to the cross-attention teacher BERT model.

cs.CL↗

arXiv2020

Particle Filtering Under General Regime Switching

In this paper, we consider a new framework for particle filtering under model uncertainty that operates beyond the scope of Markovian switching systems. Specifically, we develop a novel particle filtering algorithm that applies to general regime switching systems, where the model index is augmented as an unknown time-varying parameter in the system. The proposed approach does not require the use of multiple filters and can maintain a diverse set of particles for each considered model through appropriate choice of the particle filtering proposal distribution. The flexibility of the proposed approach allows for long-term dependencies between the models, which enables its use to a wider variety of real-world applications. We validate the method on a synthetic data experiment and show that it outperforms state-of-the-art multiple model particle filtering approaches that require the use of multiple filters.

stat.CO↗

arXiv2020

Solving Inverse Stochastic Problems from Discrete Particle Observations Using the Fokker-Planck Equation and Physics-informed Neural Networks

The Fokker-Planck (FP) equation governing the evolution of the probability density function (PDF) is applicable to many disciplines but it requires specification of the coefficients for each case, which can be functions of space-time and not just constants, hence requiring the development of a data-driven modeling approach. When the data available is directly on the PDF, then there exist methods for inverse problems that can be employed to infer the coefficients and thus determine the FP equation and subsequently obtain its solution. Herein, we address a more realistic scenario, where only sparse data are given on the particles' positions at a few time instants, which are not sufficient to accurately construct directly the PDF even at those times from existing methods, e.g., kernel estimation algorithms. To this end, we develop a general framework based on physics-informed neural networks (PINNs) that introduces a new loss function using the Kullback-Leibler divergence to connect the stochastic samples with the FP equation, to simultaneously learn the equation and infer the multi-dimensional PDF at all times. In particular, we consider two types of inverse problems, type I where the FP equation is known but the initial PDF is unknown, and type II in which, in addition to unknown initial PDF, the drift and diffusion terms are also unknown. In both cases, we investigate problems with either Brownian or Levy noise or a combination of both. We demonstrate the new PINN framework in detail in the one-dimensional case (1D) but we also provide results for up to 5D demonstrating that we can infer both the FP equation and} dynamics simultaneously at all times with high accuracy using only very few discrete observations of the particles.

physics.comp-ph↗

arXiv2020

Match$^2$: A Matching over Matching Model for Similar Question Identification

Community Question Answering (CQA) has become a primary means for people to acquire knowledge, where people are free to ask questions or submit answers. To enhance the efficiency of the service, similar question identification becomes a core task in CQA which aims to find a similar question from the archived repository whenever a new question is asked. However, it has long been a challenge to properly measure the similarity between two questions due to the inherent variation of natural language, i.e., there could be different ways to ask a same question or different questions sharing similar expressions. To alleviate this problem, it is natural to involve the existing answers for the enrichment of the archived questions. Traditional methods typically take a one-side usage, which leverages the answer as some expanded representation of the corresponding question. Unfortunately, this may introduce unexpected noises into the similarity computation since answers are often long and diverse, leading to inferior performance. In this work, we propose a two-side usage, which leverages the answer as a bridge of the two questions. The key idea is based on our observation that similar questions could be addressed by similar parts of the answer while different questions may not. In other words, we can compare the matching patterns of the two questions over the same answer to measure their similarity. In this way, we propose a novel matching over matching model, namely Match$^2$, which compares the matching patterns between two question-answer pairs for similar question identification. Empirical experiments on two benchmark datasets demonstrate that our model can significantly outperform previous state-of-the-art methods on the similar question identification task.

cs.IR↗

arXiv2020

Open-Retrieval Conversational Question Answering

Conversational search is one of the ultimate goals of information retrieval. Recent research approaches conversational search by simplified settings of response ranking and conversational question answering, where an answer is either selected from a given candidate set or extracted from a given passage. These simplifications neglect the fundamental role of retrieval in conversational search. To address this limitation, we introduce an open-retrieval conversational question answering (ORConvQA) setting, where we learn to retrieve evidence from a large collection before extracting answers, as a further step towards building functional conversational search systems. We create a dataset, OR-QuAC, to facilitate research on ORConvQA. We build an end-to-end system for ORConvQA, featuring a retriever, a reranker, and a reader that are all based on Transformers. Our extensive experiments on OR-QuAC demonstrate that a learnable retriever is crucial for ORConvQA. We further show that our system can make a substantial improvement when we enable history modeling in all system components. Moreover, we show that the reranker component contributes to the model performance by providing a regularization effect. Finally, further in-depth analyses are performed to provide new insights into ORConvQA.

cs.IR↗

arXiv2020

B-PINNs: Bayesian Physics-Informed Neural Networks for Forward and Inverse PDE Problems with Noisy Data

We propose a Bayesian physics-informed neural network (B-PINN) to solve both forward and inverse nonlinear problems described by partial differential equations (PDEs) and noisy data. In this Bayesian framework, the Bayesian neural network (BNN) combined with a PINN for PDEs serves as the prior while the Hamiltonian Monte Carlo (HMC) or the variational inference (VI) could serve as an estimator of the posterior. B-PINNs make use of both physical laws and scattered noisy measurements to provide predictions and quantify the aleatoric uncertainty arising from the noisy data in the Bayesian framework. Compared with PINNs, in addition to uncertainty quantification, B-PINNs obtain more accurate predictions in scenarios with large noise due to their capability of avoiding overfitting. We conduct a systematic comparison between the two different approaches for the B-PINN posterior estimation (i.e., HMC or VI), along with dropout used for quantifying uncertainty in deep neural networks. Our experiments show that HMC is more suitable than VI for the B-PINNs posterior estimation, while dropout employed in PINNs can hardly provide accurate predictions with reasonable uncertainty. Finally, we replace the BNN in the prior with a truncated Karhunen-Loève (KL) expansion combined with HMC or a deep normalizing flow (DNF) model as posterior estimators. The KL is as accurate as BNN and much faster but this framework cannot be easily extended to high-dimensional problems unlike the BNN based framework.

stat.ML↗

arXiv2020

Reinforcement Learning for Active Flow Control in Experiments

We demonstrate experimentally the feasibility of applying reinforcement learning (RL) in flow control problems by automatically discovering active control strategies without any prior knowledge of the flow physics. We consider the turbulent flow past a circular cylinder with the aim of reducing the cylinder drag force or maximizing the power gain efficiency by properly selecting the rotational speed of two small diameter cylinders, parallel to and located downstream of the larger cylinder. Given properly designed rewards and noise reduction techniques, after tens of towing experiments, the RL agent could discover the optimal control strategy, comparable to the optimal static control. While RL has been found to be effective in recent computer flow simulation studies, this is the first time that its effectiveness is demonstrated experimentally, paving the way for exploring new optimal active flow control strategies in complex fluid mechanics applications.

physics.flu-dyn↗

arXiv2020

Sparse Sinkhorn Attention

We propose Sparse Sinkhorn Attention, a new efficient and sparse method for learning to attend. Our method is based on differentiable sorting of internal representations. Concretely, we introduce a meta sorting network that learns to generate latent permutations over sequences. Given sorted sequences, we are then able to compute quasi-global attention with only local windows, improving the memory efficiency of the attention module. To this end, we propose new algorithmic innovations such as Causal Sinkhorn Balancing and SortCut, a dynamic sequence truncation method for tailoring Sinkhorn Attention for encoding and/or decoding purposes. Via extensive experiments on algorithmic seq2seq sorting, language modeling, pixel-wise image generation, document classification and natural language inference, we demonstrate that our memory efficient Sinkhorn Attention method is competitive with vanilla attention and consistently outperforms recently proposed efficient Transformer models such as Sparse Transformers.

cs.LG↗