arXiv subjects

Lin Liu

Publications and source records attributed to Lin Liu.

At least 253 records · Page 14Linked to original sources

arXiv2022

Low-Light Video Enhancement with Synthetic Event Guidance

Low-light video enhancement (LLVE) is an important yet challenging task with many applications such as photographing and autonomous driving. Unlike single image low-light enhancement, most LLVE methods utilize temporal information from adjacent frames to restore the color and remove the noise of the target frame. However, these algorithms, based on the framework of multi-frame alignment and enhancement, may produce multi-frame fusion artifacts when encountering extreme low light or fast motion. In this paper, inspired by the low latency and high dynamic range of events, we use synthetic events from multiple frames to guide the enhancement and restoration of low-light videos. Our method contains three stages: 1) event synthesis and enhancement, 2) event and image fusion, and 3) low-light enhancement. In this framework, we design two novel modules (event-image fusion transform and event-guided dual branch) for the second and third stages, respectively. Extensive experiments show that our method outperforms existing low-light video or single image enhancement approaches on both synthetic and real LLVE datasets.

cs.CV↗

arXiv2022

TAPE: Task-Agnostic Prior Embedding for Image Restoration

Learning a generalized prior for natural image restoration is an important yet challenging task. Early methods mostly involved handcrafted priors including normalized sparsity, l_0 gradients, dark channel priors, etc. Recently, deep neural networks have been used to learn various image priors but do not guarantee to generalize. In this paper, we propose a novel approach that embeds a task-agnostic prior into a transformer. Our approach, named Task-Agnostic Prior Embedding (TAPE), consists of two stages, namely, task-agnostic pre-training and task-specific fine-tuning, where the first stage embeds prior knowledge about natural images into the transformer and the second stage extracts the knowledge to assist downstream image restoration. Experiments on various types of degradation validate the effectiveness of TAPE. The image restoration performance in terms of PSNR is improved by as much as 1.45dB and even outperforms task-specific algorithms. More importantly, TAPE shows the ability of disentangling generalized image priors from degraded images, which enjoys favorable transfer ability to unknown downstream tasks.

cs.CV↗

arXiv2022

Local search for efficient causal effect estimation

Causal effect estimation from observational data is a challenging problem, especially with high dimensional data and in the presence of unobserved variables. The available data-driven methods for tackling the problem either provide an estimation of the bounds of a causal effect (i.e. nonunique estimation) or have low efficiency. The major hurdle for achieving high efficiency while trying to obtain unique and unbiased causal effect estimation is how to find a proper adjustment set for confounding control in a fast way, given the huge covariate space and considering unobserved variables. In this paper, we approach the problem as a local search task for finding valid adjustment sets in data. We establish the theorems to support the local search for adjustment sets, and we show that unique and unbiased estimation can be achieved from observational data even when there exist unobserved variables. We then propose a data-driven algorithm that is fast and consistent under mild assumptions. We also make use of a frequent pattern mining method to further speed up the search of minimal adjustment sets for causal effect estimation. Experiments conducted on extensive synthetic and real-world datasets demonstrate that the proposed algorithm outperforms the state-of-the-art criteria/estimators in both accuracy and time-efficiency.

stat.ME↗

arXiv2022

Secuer: ultrafast, scalable and accurate clustering of single-cell RNA-seq data

Identifying cell clusters is a critical step for single-cell transcriptomics study. Despite the numerous clustering tools developed recently, the rapid growth of scRNA-seq volumes prompts for a more (computationally) efficient clustering method. Here, we introduce Secuer, a Scalable and Efficient speCtral clUstERing algorithm for scRNA-seq data. By employing an anchor-based bipartite graph representation algorithm, Secuer enjoys reduced runtime and memory usage by orders of magnitude, especially for ultra-large datasets profiling over 1 or even 10 million cells. Meanwhile, Secuer also achieves better or comparable accuracy than competing methods in small and moderate benchmark datasets. Furthermore, we showcase that Secuer can also serve as a building block for a new consensus clustering method, Secuer-consensus, which again greatly improves the runtime and scalability of state-of-the-art consensus clustering methods while also maintaining the accuracy. Overall, Secuer is a versatile, accurate, and scalable clustering framework suitable for small to ultra-large single-cell clustering tasks.

q-bio.QM↗

arXiv2022

Explanatory causal effects for model agnostic explanations

This paper studies the problem of estimating the contributions of features to the prediction of a specific instance by a machine learning model and the overall contribution of a feature to the model. The causal effect of a feature (variable) on the predicted outcome reflects the contribution of the feature to a prediction very well. A challenge is that most existing causal effects cannot be estimated from data without a known causal graph. In this paper, we define an explanatory causal effect based on a hypothetical ideal experiment. The definition brings several benefits to model agnostic explanations. First, explanations are transparent and have causal meanings. Second, the explanatory causal effect estimation can be data driven. Third, the causal effects provide both a local explanation for a specific prediction and a global explanation showing the overall importance of a feature in a predictive model. We further propose a method using individual and combined variables based on explanatory causal effects for explanations. We show the definition and the method work with experiments on some real-world data sets.

cs.LG↗

arXiv2022

Identify treatment effect patterns for personalised decisions

In personalised decision making, evidence is required to determine whether an action (treatment) is suitable for an individual. Such evidence can be obtained by modelling treatment effect heterogeneity in subgroups. The existing interpretable modelling methods take a top-down approach to search for subgroups with heterogeneous treatment effects and they may miss the most specific and relevant context for an individual. In this paper, we design a \emph{Treatment effect pattern (TEP)} to represent treatment effect heterogeneity in data. To achieve an interpretable presentation of TEPs, we use a local causal structure around the outcome to explicitly show how those important variables are used in modelling. We also derive a formula for unbiasedly estimating the \emph{Conditional Average Causal Effect (CATE)} using the local structure in our problem setting. In the discovery process, we aim at minimising heterogeneity within each subgroup represented by a pattern. We propose a bottom-up search algorithm to discover the most specific patterns fitting individual circumstances the best for personalised decision making. Experiments show that the proposed method models treatment effect heterogeneity better than three other existing tree based methods in synthetic and real world data sets.

stat.ME↗

arXiv2022

A splitting Hamiltonian Monte Carlo method for efficient sampling

We propose a splitting Hamiltonian Monte Carlo (SHMC) algorithm, which can be computationally efficient when combined with the random mini-batch strategy. By splitting the potential energy into numerically nonstiff and stiff parts, one makes a proposal using the nonstiff part of $U$, followed by a Metropolis rejection step using the stiff part that is often easy to compute. The splitting allows efficient sampling from systems with singular potentials (or distributions with degenerate points) and/or with multiple potential barriers. In our SHMC algorithm, the proposal only based on the nonstiff part in the splitting is generated by the Hamiltonian dynamics, which can be potentially more efficient than the overdamped Langevin dynamics. We also use random batch strategies to reduce the computational cost to $\mathcal{O}(1)$ per time step in generating the proposals for problems arising from many-body systems and Bayesian inference, and prove that the errors of the Hamiltonian induced by the random batch approximation is $\mathcal{O}(\sqrt{Δt})$ in the strong and $\mathcal{O}(Δt)$ in the weak sense, where $Δt$ is the time step. Numerical experiments are conducted to verify the theoretical results and the computational efficiency of the proposed algorithms in practice.

math.NA↗

arXiv2022

Discovering Ancestral Instrumental Variables for Causal Inference from Observational Data

Instrumental variable (IV) is a powerful approach to inferring the causal effect of a treatment on an outcome of interest from observational data even when there exist latent confounders between the treatment and the outcome. However, existing IV methods require that an IV is selected and justified with domain knowledge. An invalid IV may lead to biased estimates. Hence, discovering a valid IV is critical to the applications of IV methods. In this paper, we study and design a data-driven algorithm to discover valid IVs from data under mild assumptions. We develop the theory based on partial ancestral graphs (PAGs) to support the search for a set of candidate Ancestral IVs (AIVs), and for each possible AIV, the identification of its conditioning set. Based on the theory, we propose a data-driven algorithm to discover a pair of IVs from data. The experiments on synthetic and real-world datasets show that the developed IV discovery algorithm estimates accurate estimates of causal effects in comparison with the state-of-the-art IV based causal effect estimators.

cs.AI↗

arXiv2022

NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Results

This paper reviews the challenge on constrained high dynamic range (HDR) imaging that was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2022. This manuscript focuses on the competition set-up, datasets, the proposed methods and their results. The challenge aims at estimating an HDR image from multiple respective low dynamic range (LDR) observations, which might suffer from under- or over-exposed regions and different sources of noise. The challenge is composed of two tracks with an emphasis on fidelity and complexity constraints: In Track 1, participants are asked to optimize objective fidelity scores while imposing a low-complexity constraint (i.e. solutions can not exceed a given number of operations). In Track 2, participants are asked to minimize the complexity of their solutions while imposing a constraint on fidelity scores (i.e. solutions are required to obtain a higher fidelity score than the prescribed baseline). Both tracks use the same data and metrics: Fidelity is measured by means of PSNR with respect to a ground-truth HDR image (computed both directly and with a canonical tonemapping operation), while complexity metrics include the number of Multiply-Accumulate (MAC) operations and runtime (in seconds).

cs.CV↗

arXiv2022

Global Update Guided Federated Learning

Federated learning protects data privacy and security by exchanging models instead of data. However, unbalanced data distributions among participating clients compromise the accuracy and convergence speed of federated learning algorithms. To alleviate this problem, unlike previous studies that limit the distance of updates for local models, we propose global-update-guided federated learning (FedGG), which introduces a model-cosine loss into local objective functions, so that local models can fit local data distributions under the guidance of update directions of global models. Furthermore, considering that the update direction of a global model is informative in the early stage of training, we propose adaptive loss weights based on the update distances of local models. Numerical simulations show that, compared with other advanced algorithms, FedGG has a significant improvement on model convergence accuracies and speeds. Additionally, compared with traditional fixed loss weights, adaptive loss weights enable our algorithm to be more stable and easier to implement in practice.

cs.LG↗

arXiv2022

Sequential Search with Off-Policy Reinforcement Learning

Recent years have seen a significant amount of interests in Sequential Recommendation (SR), which aims to understand and model the sequential user behaviors and the interactions between users and items over time. Surprisingly, despite the huge success Sequential Recommendation has achieved, there is little study on Sequential Search (SS), a twin learning task that takes into account a user's current and past search queries, in addition to behavior on historical query sessions. The SS learning task is even more important than the counterpart SR task for most of E-commence companies due to its much larger online serving demands as well as traffic volume. To this end, we propose a highly scalable hybrid learning model that consists of an RNN learning framework leveraging all features in short-term user-item interactions, and an attention model utilizing selected item-only features from long-term interactions. As a novel optimization step, we fit multiple short user sequences in a single RNN pass within a training batch, by solving a greedy knapsack problem on the fly. Moreover, we explore the use of off-policy reinforcement learning in multi-session personalized search ranking. Specifically, we design a pairwise Deep Deterministic Policy Gradient model that efficiently captures users' long term reward in terms of pairwise classification error. Extensive ablation experiments demonstrate significant improvement each component brings to its state-of-the-art baseline, on a variety of offline and online metrics.

cs.IR↗

arXiv2022

Assessing Classifier Fairness with Collider Bias

The increasing application of machine learning techniques in everyday decision-making processes has brought concerns about the fairness of algorithmic decision-making. This paper concerns the problem of collider bias which produces spurious associations in fairness assessment and develops theorems to guide fairness assessment avoiding the collider bias. We consider a real-world application of auditing a trained classifier by an audit agency. We propose an unbiased assessment algorithm by utilising the developed theorems to reduce collider biases in the assessment. Experiments and simulations show the proposed algorithm reduces collider biases significantly in the assessment and is promising in auditing trained classifiers.

cs.LG↗

arXiv2022

A Cooperation-Aware Lane Change Method for Autonomous Vehicles

Lane change for autonomous vehicles (AVs) is an important but challenging task in complex dynamic traffic environments. Due to difficulties in guarantee safety as well as a high efficiency, AVs are inclined to choose relatively conservative strategies for lane change. To avoid the conservatism, this paper presents a cooperation-aware lane change method utilizing interactions between vehicles. We first propose an interactive trajectory prediction method to explore possible cooperations between an AV and the others. Further, an evaluation is designed to make a decision on lane change, in which safety, efficiency and comfort are taken into consideration. Thereafter, we propose a motion planning algorithm based on model predictive control (MPC), which incorporates AV's decision and surrounding vehicles' interactive behaviors into constraints so as to avoid collisions during lane change. Quantitative testing results show that compared with the methods without an interactive prediction, our method enhances driving efficiencies of the AV and other vehicles by 14.8$\%$ and 2.6$\%$ respectively, which indicates that a proper utilization of vehicle interactions can effectively reduce the conservatism of the AV and promote the cooperation between the AV and others.

cs.RO↗

arXiv2021

Feature Selection for Efficient Local-to-Global Bayesian Network Structure Learning

Local-to-global learning approach plays an essential role in Bayesian network (BN) structure learning. Existing local-to-global learning algorithms first construct the skeleton of a DAG (directed acyclic graph) by learning the MB (Markov blanket) or PC (parents and children) of each variable in a data set, then orient edges in the skeleton. However, existing MB or PC learning methods are often computationally expensive especially with a large-sized BN, resulting in inefficient local-to-global learning algorithms. To tackle the problem, in this paper, we develop an efficient local-to-global learning approach using feature selection. Specifically, we first analyze the rationale of the well-known Minimum-Redundancy and Maximum-Relevance (MRMR) feature selection approach for learning a PC set of a variable. Based on the analysis, we propose an efficient F2SL (feature selection-based structure learning) approach to local-to-global BN structure learning. The F2SL approach first employs the MRMR approach to learn a DAG skeleton, then orients edges in the skeleton. Employing independence tests or score functions for orienting edges, we instantiate the F2SL approach into two new algorithms, F2SL-c (using independence tests) and F2SL-s (using score functions). Compared to the state-of-the-art local-to-global BN learning algorithms, the experiments validated that the proposed algorithms in this paper are more efficient and provide competitive structure learning quality than the compared algorithms.

cs.LG↗

arXiv2021

SiamTrans: Zero-Shot Multi-Frame Image Restoration with Pre-Trained Siamese Transformers

We propose a novel zero-shot multi-frame image restoration method for removing unwanted obstruction elements (such as rains, snow, and moire patterns) that vary in successive frames. It has three stages: transformer pre-training, zero-shot restoration, and hard patch refinement. Using the pre-trained transformers, our model is able to tell the motion difference between the true image information and the obstructing elements. For zero-shot image restoration, we design a novel model, termed SiamTrans, which is constructed by Siamese transformers, encoders, and decoders. Each transformer has a temporal attention layer and several self-attention layers, to capture both temporal and spatial information of multiple frames. Only pre-trained (self-supervised) on the denoising task, SiamTrans is tested on three different low-level vision tasks (deraining, demoireing, and desnowing). Compared with related methods, ours achieves the best performances, even outperforming those with supervised learning.

cs.CV↗

arXiv2021

High performance distributed feedback quantum dot lasers with laterally coupled dielectric grating

The combination of grating-based frequency-selective optical feedback mechanisms, such as distributed feedback (DFB) or distributed Bragg reflector (DBR) structures, with quantum dot (QD) gain materials is a main approach towards ultra-high-performance semiconductor lasers for many key novel applications, either as stand-alone sources or as on-chip sources in photonic integrated circuits. However, the fabrication of conventional buried Bragg grating structures on GaAs, GaAs/Si, GaSb and other material platforms have been met with major material regrowth difficulties. We report a novel and universal approach of introducing laterally coupled dielectric Bragg gratings to semiconductor lasers that allows highly controllable, reliable and strong coupling between the grating and the optical mode. We implement such a grating structure in a low-loss amorphous silicon material alongside GaAs lasers with InAs/GaAs QD gain layers. The resulting DFB laser arrays emit at pre-designed 0.8 THz LWDM frequency intervals in the 1300 nm band with record performance parameters, including side mode suppression ratios as high as 52.7 dB, continuous-wave output power of 27.7 mW (room-temperature) and 10 mW (at 70°C), and ultra-low relative intensity noise (RIN) of < -165 dB/Hz (2.5-25 GHz). The devices are also capable of operating isolator-free under very high external reflection levels of up to -12.3 dB whilst maintaining the high spectral and ultra-low RIN qualities. These results validate the novel laterally coupled dielectric grating as a technologically superior and potentially cost-effective approach for fabricating DFB and DBR lasers free of their semiconductor material constraints, thus universally applicable across different material platforms and wavelength bands.

physics.optics↗

arXiv2021

A unified survey of treatment effect heterogeneity modeling and uplift modeling

A central question in many fields of scientific research is to determine how an outcome would be affected by an action, or to measure the effect of an action (a.k.a treatment effect). In recent years, a need for estimating the heterogeneous treatment effects conditioning on the different characteristics of individuals has emerged from research fields such as personalized healthcare, social science, and online marketing. To meet the need, researchers and practitioners from different communities have developed algorithms by taking the treatment effect heterogeneity modeling approach and the uplift modeling approach, respectively. In this paper, we provide a unified survey of these two seemingly disconnected yet closely related approaches under the potential outcome framework. We then provide a structured survey of existing methods by emphasizing on their inherent connections with a set of unified notations to make comparisons of the different methods easy. We then review the main applications of the surveyed methods in personalized marketing, personalized medicine, and social studies. Finally, we summarize the existing software packages and present discussions based on the use of methods on synthetic, semi-synthetic and real world data sets and provide some general guidelines for choosing methods.

stat.ME↗

arXiv2021

Switching magnon chirality in artificial antiferromagnet

Magnons in antiferromagnets can support both right-handed and left-handed chiralities, which shed a light on the chirality-based spintronics. Here we demonstrate the switching and reading of magnon chirality in an artificial antiferromagnet. The coexisting antiferromagnetic and ferromagnetic characteristic resonance modes are discovered, which permits a high tunability in the modulation of magnon chirality. The reading of the chirality is accomplished via the chirality-dependent spin pumping as well as spin rectification effect. Our result illustrates an ideal antiferromagnetic platform for handling magnon chirality and paves the way for chirality-based spintronics.

physics.app-ph↗