arXiv subjects

Haoran Liu

Publications and source records attributed to Haoran Liu.

86 records · Page 5Linked to original sources

arXiv2023

Delving into Discrete Normalizing Flows on SO(3) Manifold for Probabilistic Rotation Modeling

Normalizing flows (NFs) provide a powerful tool to construct an expressive distribution by a sequence of trackable transformations of a base distribution and form a probabilistic model of underlying data. Rotation, as an important quantity in computer vision, graphics, and robotics, can exhibit many ambiguities when occlusion and symmetry occur and thus demands such probabilistic models. Though much progress has been made for NFs in Euclidean space, there are no effective normalizing flows without discontinuity or many-to-one mapping tailored for SO(3) manifold. Given the unique non-Euclidean properties of the rotation manifold, adapting the existing NFs to SO(3) manifold is non-trivial. In this paper, we propose a novel normalizing flow on SO(3) by combining a Mobius transformation-based coupling layer and a quaternion affine transformation. With our proposed rotation normalizing flows, one can not only effectively express arbitrary distributions on SO(3), but also conditionally build the target distribution given input observations. Extensive experiments show that our rotation normalizing flows significantly outperform the baselines on both unconditional and conditional tasks.

cs.CV↗

arXiv2023

UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy

In this work, we tackle the problem of learning universal robotic dexterous grasping from a point cloud observation under a table-top setting. The goal is to grasp and lift up objects in high-quality and diverse ways and generalize across hundreds of categories and even the unseen. Inspired by successful pipelines used in parallel gripper grasping, we split the task into two stages: 1) grasp proposal (pose) generation and 2) goal-conditioned grasp execution. For the first stage, we propose a novel probabilistic model of grasp pose conditioned on the point cloud observation that factorizes rotation from translation and articulation. Trained on our synthesized large-scale dexterous grasp dataset, this model enables us to sample diverse and high-quality dexterous grasp poses for the object point cloud.For the second stage, we propose to replace the motion planning used in parallel gripper grasping with a goal-conditioned grasp policy, due to the complexity involved in dexterous grasping execution. Note that it is very challenging to learn this highly generalizable grasp policy that only takes realistic inputs without oracle states. We thus propose several important innovations, including state canonicalization, object curriculum, and teacher-student distillation. Integrating the two stages, our final pipeline becomes the first to achieve universal generalization for dexterous grasping, demonstrating an average success rate of more than 60\% on thousands of object instances, which significantly outperforms all baselines, meanwhile showing only a minimal generalization gap.

cs.RO↗

arXiv2023

Learning Hierarchical Protein Representations via Complete 3D Graph Networks

We consider representation learning for proteins with 3D structures. We build 3D graphs based on protein structures and develop graph networks to learn their representations. Depending on the levels of details that we wish to capture, protein representations can be computed at different levels, \emph{e.g.}, the amino acid, backbone, or all-atom levels. Importantly, there exist hierarchical relations among different levels. In this work, we propose to develop a novel hierarchical graph network, known as ProNet, to capture the relations. Our ProNet is very flexible and can be used to compute protein representations at different levels of granularity. By treating each amino acid as a node in graph modeling as well as harnessing the inherent hierarchies, our ProNet is more effective and efficient than existing methods. We also show that, given a base 3D graph network that is complete, our ProNet representations are also complete at all levels. Experimental results show that ProNet outperforms recent methods on most datasets. In addition, results indicate that different downstream tasks may require representations at different levels. Our code is publicly available as part of the DIG library (\url{https://github.com/divelab/DIG}).

cs.LG↗

arXiv2023

Gradient-Guided Importance Sampling for Learning Binary Energy-Based Models

Learning energy-based models (EBMs) is known to be difficult especially on discrete data where gradient-based learning strategies cannot be applied directly. Although ratio matching is a sound method to learn discrete EBMs, it suffers from expensive computation and excessive memory requirements, thereby resulting in difficulties in learning EBMs on high-dimensional data. Motivated by these limitations, in this study, we propose ratio matching with gradient-guided importance sampling (RMwGGIS). Particularly, we use the gradient of the energy function w.r.t. the discrete data space to approximately construct the provably optimal proposal distribution, which is subsequently used by importance sampling to efficiently estimate the original ratio matching objective. We perform experiments on density modeling over synthetic discrete data, graph generation, and training Ising models to evaluate our proposed method. The experimental results demonstrate that our method can significantly alleviate the limitations of ratio matching, perform more effectively in practice, and scale to high-dimensional problems. Our implementation is available at https://github.com/divelab/RMwGGIS.

cs.LG↗

arXiv2023

Buoyancy-driven attraction of active droplets

Active oil droplets in a liquid are believed to repel due to the Marangoni effect, while buoyancy effects caused by the density difference between the droplets, diffusing product, and ambient fluid are usually overlooked. Recent experiments have observed active droplet clustering phenomena due to buoyancy-driven convection (Kruger et al. Eur. Phys. J. E, vol. 39, 2016, pp.1-9). In this study, we numerically analyze the buoyancy effect in addition to Marangoni flow, characterized by Peclet number $Pe$. The buoyancy effects originate from (i) the density difference between the droplet and the ambient liquid, which is characterized by Galileo number $Ga$, and (ii) the density difference between the diffusing product (i.e. filled micelles) and the ambient liquid, characterized by a solutal Rayleigh number $Ra$. We analyze how the attracting and repulsing behavior depends on the control parameters $Pe$, $Ga$, and $Ra$. We find that while Marangoni flow causes repulsion, the buoyancy effect leads to attraction, and even collisions can take place at high Ra. We also observe a delayed collision as $Ga$ increases. Moreover, we derive that the attracting velocity, characterized by a Reynolds number $Re_d$, is proportional to $Ra^{1/4}/(l/R)$, where $l/R$ is the normalized distance by radius between neighboring droplets. Finally, we obtain repulsive velocity, characterized by $Re_{rep}$, as proportional to $PeRa^{-0.38}$. The balance of attractive and repulsive effects results in $Pe \sim Ra^{0.63}$, which agrees with the transition curve between regimes with and without collision.

physics.flu-dyn↗

arXiv2022

FECAM: Frequency Enhanced Channel Attention Mechanism for Time Series Forecasting

Time series forecasting is a long-standing challenge due to the real-world information is in various scenario (e.g., energy, weather, traffic, economics, earthquake warning). However some mainstream forecasting model forecasting result is derailed dramatically from ground truth. We believe it's the reason that model's lacking ability of capturing frequency information which richly contains in real world datasets. At present, the mainstream frequency information extraction methods are Fourier transform(FT) based. However, use of FT is problematic due to Gibbs phenomenon. If the values on both sides of sequences differ significantly, oscillatory approximations are observed around both sides and high frequency noise will be introduced. Therefore We propose a novel frequency enhanced channel attention that adaptively modelling frequency interdependencies between channels based on Discrete Cosine Transform which would intrinsically avoid high frequency noise caused by problematic periodity during Fourier Transform, which is defined as Gibbs Phenomenon. We show that this network generalize extremely effectively across six real-world datasets and achieve state-of-the-art performance, we further demonstrate that frequency enhanced channel attention mechanism module can be flexibly applied to different networks. This module can improve the prediction ability of existing mainstream networks, which reduces 35.99% MSE on LSTM, 10.01% on Reformer, 8.71% on Informer, 8.29% on Autoformer, 8.06% on Transformer, etc., at a slight computational cost ,with just a few line of code. Our codes and data are available at https://github.com/Zero-coder/FECAM.

cs.AI↗

arXiv2022

A sample-position-autocorrection system with precision better than 1 \um~in angle-resolved photoemission experiments

We present the development of a high-precision sample-position-autocorrection system for photoemission experiments. A binocular vision method based on image pattern matching calculations was realized to track the sample position with an accuracy better than 1 \um, which was much smaller than the spot size of the incident laser. We illustrate the performance of the sample-position-autocorrection system with representative photoemission data on the topological insulator Bi$_2$Se$_3$ and an optimally-doped cuprate superconductor \Bi. Our method provides new possibilities for studying the temperature-dependent electronic structures in quantum materials by laser-based or spatially resolved photoemission systems with high precision and efficiency.

cond-mat.supr-con↗

arXiv2022

ComENet: Towards Complete and Efficient Message Passing for 3D Molecular Graphs

Many real-world data can be modeled as 3D graphs, but learning representations that incorporates 3D information completely and efficiently is challenging. Existing methods either use partial 3D information, or suffer from excessive computational cost. To incorporate 3D information completely and efficiently, we propose a novel message passing scheme that operates within 1-hop neighborhood. Our method guarantees full completeness of 3D information on 3D graphs by achieving global and local completeness. Notably, we propose the important rotation angles to fulfill global completeness. Additionally, we show that our method is orders of magnitude faster than prior methods. We provide rigorous proof of completeness and analysis of time complexity for our methods. As molecules are in essence quantum systems, we build the \underline{com}plete and \underline{e}fficient graph neural network (ComENet) by combing quantum inspired basis functions and the proposed message passing scheme. Experimental results demonstrate the capability and efficiency of ComENet, especially on real-world datasets that are large in both numbers and sizes of graphs. Our code is publicly available as part of the DIG library (\url{https://github.com/divelab/DIG}).

cs.LG↗

arXiv2022

A CutFEM divergence-free discretization for the Stokes problem

We construct and analyze a CutFEM discretization for the Stokes problem based on the Scott-Vogelius pair. The discrete piecewise polynomial spaces are defined on macro-element triangulations which are not fitted to the smooth physical domain. Boundary conditions are imposed via penalization through the help of a Nitsche-type discretization, whereas stability with respect to small and anisotropic cuts of the bulk elements is ensured by adding local ghost penalty stabilization terms. We show stability of the scheme as well as a divergence--free property of the discrete velocity outside an $O(h)$ neighborhood of the boundary. To mitigate the error caused by the violation of the divergence-free condition, we introduce local grad-div stabilization. The error analysis shows that the grad-div parameter can scale like $O(h^{-1})$, allowing a rather heavy penalty for the violation of mass conservation, while still ensuring optimal order error estimates.

math.NA↗

arXiv2021

DIG: A Turnkey Library for Diving into Graph Deep Learning Research

Although there exist several libraries for deep learning on graphs, they are aiming at implementing basic operations for graph deep learning. In the research community, implementing and benchmarking various advanced tasks are still painful and time-consuming with existing libraries. To facilitate graph deep learning research, we introduce DIG: Dive into Graphs, a turnkey library that provides a unified testbed for higher level, research-oriented graph deep learning tasks. Currently, we consider graph generation, self-supervised learning on graphs, explainability of graph neural networks, and deep learning on 3D graphs. For each direction, we provide unified implementations of data interfaces, common algorithms, and evaluation metrics. Altogether, DIG is an extensible, open-source, and turnkey library for researchers to develop new methods and effortlessly compare with common baselines using widely used datasets and evaluation metrics. Source code is available at https://github.com/divelab/DIG.

cs.LG↗

arXiv2021

Exploring the Common Principal Subspace of Deep Features in Neural Networks

We find that different Deep Neural Networks (DNNs) trained with the same dataset share a common principal subspace in latent spaces, no matter in which architectures (e.g., Convolutional Neural Networks (CNNs), Multi-Layer Preceptors (MLPs) and Autoencoders (AEs)) the DNNs were built or even whether labels have been used in training (e.g., supervised, unsupervised, and self-supervised learning). Specifically, we design a new metric $\mathcal{P}$-vector to represent the principal subspace of deep features learned in a DNN, and propose to measure angles between the principal subspaces using $\mathcal{P}$-vectors. Small angles (with cosine close to $1.0$) have been found in the comparisons between any two DNNs trained with different algorithms/architectures. Furthermore, during the training procedure from random scratch, the angle decrease from a larger one ($70^\circ-80^\circ$ usually) to the small one, which coincides the progress of feature space learning from scratch to convergence. Then, we carry out case studies to measure the angle between the $\mathcal{P}$-vector and the principal subspace of training dataset, and connect such angle with generalization performance. Extensive experiments with practically-used Multi-Layer Perceptron (MLPs), AEs and CNNs for classification, image reconstruction, and self-supervised learning tasks on MNIST, CIFAR-10 and CIFAR-100 datasets have been done to support our claims with solid evidences. Interpretability of Deep Learning, Feature Learning, and Subspaces of Deep Features

cs.LG↗

arXiv2021

A divergence-free finite element method for the Stokes problem with boundary correction

This paper constructs and analyzes a boundary correction finite element method for the Stokes problem based on the Scott-Vogelius pair on Clough-Tocher splits. The velocity space consists of continuous piecewise quadratic polynomials, and the pressure space consists of piecewise linear polynomials without continuity constraints. A Lagrange multiplier space that consists of continuous piecewise quadratic polynomials with respect to boundary partition is introduced to enforce boundary conditions as well as to mitigate the lack of pressure-robustness. We prove several inf-sup conditions, leading to the well-posedness of the method. In addition, we show that the method converges with optimal order and the velocity approximation is divergence free.

math.NA↗

arXiv2018

Neural Diffusion Model for Microscopic Cascade Prediction

The prediction of information diffusion or cascade has attracted much attention over the last decade. Most cascade prediction works target on predicting cascade-level macroscopic properties such as the final size of a cascade. Existing microscopic cascade prediction models which focus on user-level modeling either make strong assumptions on how a user gets infected by a cascade or limit themselves to a specific scenario where "who infected whom" information is explicitly labeled. The strong assumptions oversimplify the complex diffusion mechanism and prevent these models from better fitting real-world cascade data. Also, the methods which focus on specific scenarios cannot be generalized to a general setting where the diffusion graph is unobserved. To overcome the drawbacks of previous works, we propose a Neural Diffusion Model (NDM) for general microscopic cascade prediction. NDM makes relaxed assumptions and employs deep learning techniques including attention mechanism and convolutional network for cascade modeling. Both advantages enable our model to go beyond the limitations of previous methods, better fit the diffusion data and generalize to unseen cascades. Experimental results on diffusion prediction task over four realistic cascade datasets show that our model can achieve a relative improvement up to 26% against the best performing baseline in terms of F1 score.

cs.SI↗

arXiv2018

A Blended Deep Learning Approach for Predicting User Intended Actions

User intended actions are widely seen in many areas. Forecasting these actions and taking proactive measures to optimize business outcome is a crucial step towards sustaining the steady business growth. In this work, we focus on pre- dicting attrition, which is one of typical user intended actions. Conventional attrition predictive modeling strategies suffer a few inherent drawbacks. To overcome these limitations, we propose a novel end-to-end learning scheme to keep track of the evolution of attrition patterns for the predictive modeling. It integrates user activity logs, dynamic and static user profiles based on multi-path learning. It exploits historical user records by establishing a decaying multi-snapshot technique. And finally it employs the precedent user intentions via guiding them to the subsequent learning procedure. As a result, it addresses all disadvantages of conventional methods. We evaluate our methodology on two public data repositories and one private user usage dataset provided by Adobe Creative Cloud. The extensive experiments demonstrate that it can offer the appealing performance in comparison with several existing approaches as rated by different popular metrics. Furthermore, we introduce an advanced interpretation and visualization strategy to effectively characterize the periodicity of user activity logs. It can help to pinpoint important factors that are critical to user attrition and retention and thus suggests actionable improvement targets for business practice. Our work will provide useful insights into the prediction and elucidation of other user intended actions as well.

cs.LG↗