Searcharxiv⌕ Search

arXiv subjects

Bowen Li

Publications and source records attributed to Bowen Li.

At least 163 records · Page 9Linked to original sources
arXiv2023

An Investigation of LLMs' Inefficacy in Understanding Converse Relations

Large Language Models (LLMs) have achieved remarkable success in many formal language oriented tasks, such as structural data-to-text and semantic parsing. However current benchmarks mostly follow the data distribution of the pre-training data of LLMs. Therefore, a natural question rises that do LLMs really understand the structured semantics of formal languages. In this paper, we investigate this problem on a special case, converse binary relation. We introduce a new benchmark ConvRe focusing on converse relations, which contains 17 relations and 1240 triples extracted from popular knowledge graph completion datasets. Our ConvRE features two tasks, Re2Text and Text2Re, which are formulated as multi-choice question answering to evaluate LLMs' ability to determine the matching between relations and associated text. For the evaluation protocol, apart from different prompting methods, we further introduce variants to the test text and few-shot example text. We conduct experiments on three popular LLM families and have observed various scaling trends. The results suggest that LLMs often resort to shortcut learning and still face challenges on our proposed benchmark.

cs.CL↗
arXiv2023

BatmanNet: Bi-branch Masked Graph Transformer Autoencoder for Molecular Representation

Although substantial efforts have been made using graph neural networks (GNNs) for AI-driven drug discovery (AIDD), effective molecular representation learning remains an open challenge, especially in the case of insufficient labeled molecules. Recent studies suggest that big GNN models pre-trained by self-supervised learning on unlabeled datasets enable better transfer performance in downstream molecular property prediction tasks. However, the approaches in these studies require multiple complex self-supervised tasks and large-scale datasets, which are time-consuming, computationally expensive, and difficult to pre-train end-to-end. Here, we design a simple yet effective self-supervised strategy to simultaneously learn local and global information about molecules, and further propose a novel bi-branch masked graph transformer autoencoder (BatmanNet) to learn molecular representations. BatmanNet features two tailored complementary and asymmetric graph autoencoders to reconstruct the missing nodes and edges, respectively, from a masked molecular graph. With this design, BatmanNet can effectively capture the underlying structure and semantic information of molecules, thus improving the performance of molecular representation. BatmanNet achieves state-of-the-art results for multiple drug discovery tasks, including molecular properties prediction, drug-drug interaction, and drug-target interaction, on 13 benchmark datasets, demonstrating its great potential and superiority in molecular representation learning.

cs.LG↗
arXiv2023

Causal Document-Grounded Dialogue Pre-training

The goal of document-grounded dialogue (DocGD) is to generate a response by grounding the evidence in a supporting document in accordance with the dialogue context. This process involves four variables that are causally connected. Recently, task-specific pre-training has greatly boosted performances on many downstream tasks. Existing DocGD methods, however, continue to rely on general pre-trained language models without a specifically tailored pre-training approach that explicitly captures the causal relationships. To tackle this issue, we are the first to present a causally-complete dataset construction strategy for building million-level DocGD pre-training corpora. To better capture causality, we further propose a causally-perturbed pre-training strategy, which introduces causal perturbations on the variables and optimizes the overall causal effect. Experiments on three benchmark datasets demonstrate that our causal pre-training achieves considerable and consistent improvements under fully-supervised, low-resource, few-shot, and zero-shot settings.

cs.CL↗
arXiv2023

GPU-Accelerated Sequential Quadratic Programming Algorithm for Solving ACOPF

Sequential quadratic programming (SQP) is widely used in solving nonlinear optimization problem, with advantages of warm-starting solutions, as well as finding high-accurate solution and converging quadratically using second-order information, such as the Hessian matrix. In this study we develop a scalable SQP algorithm for solving the alternate current optimal power flow problem (ACOPF), leveraging the parallel computing capabilities of graphics processing units (GPUs). Our methodology incorporates the alternating direction method of multipliers (ADMM) to initialize and decompose the quadratic programming subproblems within each SQP iteration into independent small subproblems for each electric grid component. We have implemented the proposed SQP algorithm using our portable Julia package ExaAdmm.jl, which solves the ADMM subproblems in parallel on all major GPU architectures. For numerical experiments, we compared three solution approaches: (i) the SQP algorithm with a GPU-based ADMM subproblem solver, (ii) a CPU-based ADMM solver, and (iii) the QP solver Ipopt (the state-of-the-art interior point solver) and observed that for larger instances our GPU-based SQP solver efficiently leverages the GPU many-core architecture, dramatically reducing the solution time.

math.OC↗
arXiv2023

On a general matrix-valued unbalanced optimal transport problem

We introduce a general class of transport distances ${\rm WB}_Λ$ over the space of positive semi-definite matrix-valued Radon measures $\mathcal{M}(Ω,\mathbb{S}_+^n)$, called the weighted Wasserstein-Bures distance. Such a distance is defined via a generalized Benamou-Brenier formulation with a weighted action functional and an abstract matricial continuity equation, which leads to a convex optimization problem. Some recently proposed models, including the Kantorovich-Bures distance and the Wasserstein-Fisher-Rao distance, can naturally fit into ours. We give a complete characterization of the minimizer and explore the topological and geometrical properties of the space $(\mathcal{M}(Ω,\mathbb{S}_+^n),{\rm WB}_Λ)$. In particular, we show that $(\mathcal{M}(Ω,\mathbb{S}_+^n),{\rm WB}_Λ)$ is a complete geodesic space and exhibits a conic structure.

math.NA↗
arXiv2023

VoxDet: Voxel Learning for Novel Instance Detection

Detecting unseen instances based on multi-view templates is a challenging problem due to its open-world nature. Traditional methodologies, which primarily rely on 2D representations and matching techniques, are often inadequate in handling pose variations and occlusions. To solve this, we introduce VoxDet, a pioneer 3D geometry-aware framework that fully utilizes the strong 3D voxel representation and reliable voxel matching mechanism. VoxDet first ingeniously proposes template voxel aggregation (TVA) module, effectively transforming multi-view 2D images into 3D voxel features. By leveraging associated camera poses, these features are aggregated into a compact 3D template voxel. In novel instance detection, this voxel representation demonstrates heightened resilience to occlusion and pose variations. We also discover that a 3D reconstruction objective helps to pre-train the 2D-3D mapping in TVA. Second, to quickly align with the template voxel, VoxDet incorporates a Query Voxel Matching (QVM) module. The 2D queries are first converted into their voxel representation with the learned 2D-3D mapping. We find that since the 3D voxel representations encode the geometry, we can first estimate the relative rotation and then compare the aligned voxels, leading to improved accuracy and efficiency. In addition to method, we also introduce the first instance detection benchmark, RoboTools, where 20 unique instances are video-recorded with camera extrinsic. RoboTools also provides 24 challenging cluttered scenarios with more than 9k box annotations. Exhaustive experiments are conducted on the demanding LineMod-Occlusion, YCB-video, and RoboTools benchmarks, where VoxDet outperforms various 2D baselines remarkably with faster speed. To the best of our knowledge, VoxDet is the first to incorporate implicit 3D knowledge for 2D novel instance detection tasks.

cs.CV↗
arXiv2023

Vector-wise Joint Diagonalization of Almost Commuting Matrices

This work aims to numerically construct exactly commuting matrices close to given almost commuting ones, which is equivalent to the joint approximate diagonalization problem. We first prove that almost commuting matrices generically have approximate common eigenvectors that are almost orthogonal to each other. Based on this key observation, we propose a fast and robust vector-wise joint diagonalization (VJD) algorithm, which constructs the orthogonal similarity transform by sequentially finding these approximate common eigenvectors. In doing so, we consider sub-optimization problems over the unit sphere, for which we present a Riemannian quasi-Newton method with rigorous convergence analysis. We also discuss the numerical stability of the proposed VJD algorithm. Numerical examples with applications in independent component analysis are provided to reveal the relation with Huaxin Lin's theorem and to demonstrate that our method compares favorably with the state-of-the-art Jacobi-type joint diagonalization algorithm.

math.NA↗
arXiv2023

Fano resonances in all-dielectric electromagnetic metasurfaces

We are interested in the resonant electromagnetic (EM) scattering by all-dielectric metasurfaces made of a two-dimensional lattice of nanoparticles with high refractive indices. In [Ammari et al., Trans. AMS, 376 (2023), 39-90], it has been shown that a single high-index nanoresonator can couple with the incident wave and exhibit a strong magnetic dipole response. Recent physics experiments reveal that when the particles are arranged in certain periodic configurations, they may have different anomalous scattering effects in the macroscopic scale, compared to the single-particle case. In this work, we shall develop a rigorous mathematical framework for analyzing the resonant behaviors of all-dielectric metasurfaces. We start with the characterization of subwavelength scattering resonances in such a periodic setting and their asymptotic expansions in terms of the refractive index of the nanoparticles. Then we show that real resonances always exist below the essential spectrum of the periodic Maxwell operator and that they are the simple poles of the scattering resolvent with the exponentially decaying resonant modes. By using group theory, we discuss the implications of the symmetry of the metasurface on the subwavelength band functions and their associated eigenfunctions. For the symmetric metasurfaces with the normal incidence, we use a variational method to show the existence of embedded eigenvalues (i.e., real subwavelength resonances embedded in the continuous radiation spectrum). Furthermore, we break the configuration symmetry either by introducing a small deformation of particles or by slightly deviating from the normal incidence and prove that Fano-type reflection and transmission anomalies can arise in both of these scenarios.

physics.optics↗
arXiv2023

An Improved Greedy Curvature Bound in Finite-Horizon String Optimization with Application to a Sensor Coverage Problem

We study the optimization problem of choosing strings of finite length to maximize string submodular functions on string matroids, which is a broader class of problems than maximizing set submodular functions on set matroids. We provide a lower bound for the performance of the greedy algorithm in our problem, and then prove that our bound is superior to the greedy curvature bound of Conforti and Cornuejols. Our bound has lower computational complexity than most previously proposed curvature bounds. Finally, we demonstrate the strength of our result on a sensor coverage problem.

cs.DS↗
arXiv2023

Early Detection and Localization of Pancreatic Cancer by Label-Free Tumor Synthesis

Early detection and localization of pancreatic cancer can increase the 5-year survival rate for patients from 8.5% to 20%. Artificial intelligence (AI) can potentially assist radiologists in detecting pancreatic tumors at an early stage. Training AI models require a vast number of annotated examples, but the availability of CT scans obtaining early-stage tumors is constrained. This is because early-stage tumors may not cause any symptoms, which can delay detection, and the tumors are relatively small and may be almost invisible to human eyes on CT scans. To address this issue, we develop a tumor synthesis method that can synthesize enormous examples of small pancreatic tumors in the healthy pancreas without the need for manual annotation. Our experiments demonstrate that the overall detection rate of pancreatic tumors, measured by Sensitivity and Specificity, achieved by AI trained on synthetic tumors is comparable to that of real tumors. More importantly, our method shows a much higher detection rate for small tumors. We further investigate the per-voxel segmentation performance of pancreatic tumors if AI is trained on a combination of CT scans with synthetic tumors and CT scans with annotated large tumors at an advanced stage. Finally, we show that synthetic tumors improve AI generalizability in tumor detection and localization when processing CT scans from different hospitals. Overall, our proposed tumor synthesis method has immense potential to improve the early detection of pancreatic cancer, leading to better patient outcomes.

eess.IV↗
arXiv2023

PVT++: A Simple End-to-End Latency-Aware Visual Tracking Framework

Visual object tracking is essential to intelligent robots. Most existing approaches have ignored the online latency that can cause severe performance degradation during real-world processing. Especially for unmanned aerial vehicles (UAVs), where robust tracking is more challenging and onboard computation is limited, the latency issue can be fatal. In this work, we present a simple framework for end-to-end latency-aware tracking, i.e., end-to-end predictive visual tracking (PVT++). Unlike existing solutions that naively append Kalman Filters after trackers, PVT++ can be jointly optimized, so that it takes not only motion information but can also leverage the rich visual knowledge in most pre-trained tracker models for robust prediction. Besides, to bridge the training-evaluation domain gap, we propose a relative motion factor, empowering PVT++ to generalize to the challenging and complex UAV tracking scenes. These careful designs have made the small-capacity lightweight PVT++ a widely effective solution. Additionally, this work presents an extended latency-aware evaluation benchmark for assessing an any-speed tracker in the online setting. Empirical results on a robotic platform from the aerial perspective show that PVT++ can achieve significant performance gain on various trackers and exhibit higher accuracy than prior solutions, largely mitigating the degradation brought by latency.

cs.CV↗
arXiv2023

Interpolation between modified logarithmic Sobolev and Poincare inequalities for quantum Markovian dynamics

We define the quantum $p$-divergences and introduce Beckner's inequalities for primitive quantum Markov semigroups on a finite-dimensional matrix algebra satisfying the detailed balance condition. Such inequalities quantify the convergence rate of the quantum dynamics in the noncommutative $L_p$-norm. We obtain a number of implications between Beckner's inequalities and other quantum functional inequalities, as well as the hypercontractivity. In particular, we show that the quantum Beckner's inequalities interpolate between the Sobolev-type inequalities and the Poincaré inequality in a sharp way. We provide a uniform lower bound for the Beckner constant $α_p$ in terms of the spectral gap and establish the stability of $α_p$ with respect to the invariant state. As applications, we compute the Beckner constant for the depolarizing semigroup and discuss the mixing time. For symmetric quantum Markov semigroups, we derive the moment estimate, which further implies a concentration inequality. We introduce a new class of quantum transport distances $W_{2,p}$ interpolating the quantum 2-Wasserstein distance by Carlen and Maas [J. Funct. Anal. 273(5), 1810-1869 (2017)] and a noncommutative $\dot{H}^{-1}$ Sobolev distance. We show that the quantum Markov semigroup with $σ$-GNS detailed balance is the gradient flow of a quantum $p$-divergence with respect to the metric $W_{2,p}$. We prove that the set of quantum states equipped with $W_{2,p}$ is a complete geodesic space. We then consider the associated entropic Ricci curvature lower bound via the geodesic convexity of $p$-divergence, and obtain an HWI-type interpolation inequality. This enables us to prove that the positive Ricci curvature implies the quantum Beckner's inequality, from which a transport cost and Poincaré inequalities can follow.

math.OA↗
arXiv2023

Temporal Gradient Inversion Attacks with Robust Optimization

Federated Learning (FL) has emerged as a promising approach for collaborative model training without sharing private data. However, privacy concerns regarding information exchanged during FL have received significant research attention. Gradient Inversion Attacks (GIAs) have been proposed to reconstruct the private data retained by local clients from the exchanged gradients. While recovering private data, the data dimensions and the model complexity increase, which thwart data reconstruction by GIAs. Existing methods adopt prior knowledge about private data to overcome those challenges. In this paper, we first observe that GIAs with gradients from a single iteration fail to reconstruct private data due to insufficient dimensions of leaked gradients, complex model architectures, and invalid gradient information. We investigate a Temporal Gradient Inversion Attack with a Robust Optimization framework, called TGIAs-RO, which recovers private data without any prior knowledge by leveraging multiple temporal gradients. To eliminate the negative impacts of outliers, e.g., invalid gradients for collaborative optimization, robust statistics are proposed. Theoretical guarantees on the recovery performance and robustness of TGIAs-RO against invalid gradients are also provided. Extensive empirical results on MNIST, CIFAR10, ImageNet and Reuters 21578 datasets show that the proposed TGIAs-RO with 10 temporal gradients improves reconstruction performance compared to state-of-the-art methods, even for large batch sizes (up to 128), complex models like ResNet18, and large datasets like ImageNet (224*224 pixels). Furthermore, the proposed attack method inspires further exploration of privacy-preserving methods in the context of FL.

cs.LG↗
arXiv2023

History Semantic Graph Enhanced Conversational KBQA with Temporal Information Modeling

Context information modeling is an important task in conversational KBQA. However, existing methods usually assume the independence of utterances and model them in isolation. In this paper, we propose a History Semantic Graph Enhanced KBQA model (HSGE) that is able to effectively model long-range semantic dependencies in conversation history while maintaining low computational cost. The framework incorporates a context-aware encoder, which employs a dynamic memory decay mechanism and models context at different levels of granularity. We evaluate HSGE on a widely used benchmark dataset for complex sequential question answering. Experimental results demonstrate that it outperforms existing baselines averaged on all question types.

cs.CL↗
arXiv2023

EduChain: A Blockchain-based Education Data Management System

The predominant centralized paradigm in educational data management currently suffers from several critical issues such as vulnerability to malicious tampering, a high prevalence of diploma counterfeiting, and the onerous cost of certificate authentication. Decentralized blockchain technology, with its cutting-edge capabilities, presents a viable solution to these pervasive problems. In this paper, we illuminate the inherent limitations of existing centralized systems and introduce EduChain, a novel heterogeneous blockchain-based system for managing educational data. EduChain uniquely harnesses the strengths of both private and consortium blockchains, offering an unprecedented level of security and efficiency. In addition, we propose a robust mechanism for performing database consistency checks and error tracing. This is achieved through the implementation of a secondary consensus, employing the pt-table-checksum tool. This approach effectively addresses the prevalent issue of database mismatches. Our system demonstrates superior performance in key areas such as information verification, error traceback, and data security, thereby significantly improving the integrity and trustworthiness of educational data management. Through EduChain, we offer a powerful solution for future advancements in secure and efficient educational data management.

cs.CR↗
arXiv2023

Quantum variational embedding for ground-state energy problems: sum of squares and cluster selection

We introduce a sum-of-squares SDP hierarchy approximating the ground-state energy from below for quantum many-body problems, with a natural quantum embedding interpretation. We establish the connections between our approach and other variational methods for lower bounds, including the variational embedding, the RDM method in quantum chemistry, and the Anderson bounds. Additionally, inspired by the quantum information theory, we propose efficient strategies for optimizing cluster selection to tighten SDP relaxations while staying within a computational budget. Numerical experiments are presented to demonstrate the effectiveness of our strategy. As a byproduct of our investigation, we find that quantum entanglement has the potential to capture the underlying graph of the many-body Hamiltonian.

quant-ph↗
arXiv2023

Label-Assemble: Leveraging Multiple Datasets with Partial Labels

The success of deep learning relies heavily on large labeled datasets, but we often only have access to several small datasets associated with partial labels. To address this problem, we propose a new initiative, "Label-Assemble", that aims to unleash the full potential of partial labels from an assembly of public datasets. We discovered that learning from negative examples facilitates both computer-aided disease diagnosis and detection. This discovery will be particularly crucial in novel disease diagnosis, where positive examples are hard to collect, yet negative examples are relatively easier to assemble. For example, assembling existing labels from NIH ChestX-ray14 (available since 2017) significantly improves the accuracy of COVID-19 diagnosis from 96.3% to 99.3%. In addition to diagnosis, assembling labels can also improve disease detection, e.g., the detection of pancreatic ductal adenocarcinoma (PDAC) can greatly benefit from leveraging the labels of Cysts and PanNets (two other types of pancreatic abnormalities), increasing sensitivity from 52.1% to 84.0% while maintaining a high specificity of 98.0%.

cs.CV↗
arXiv2023

AirLoc: Object-based Indoor Relocalization

Indoor relocalization is vital for both robotic tasks like autonomous exploration and civil applications such as navigation with a cell phone in a shopping mall. Some previous approaches adopt geometrical information such as key-point features or local textures to carry out indoor relocalization, but they either easily fail in an environment with visually similar scenes or require many database images. Inspired by the fact that humans often remember places by recognizing unique landmarks, we resort to objects, which are more informative than geometry elements. In this work, we propose a simple yet effective object-based indoor relocalization approach, dubbed AirLoc. To overcome the critical challenges of object reidentification and remembering object relationships, we extract object-wise appearance embedding and inter-object geometric relationships. The geometry and appearance features are integrated to generate cumulative scene features. This results in a robust, accurate, and portable indoor relocalization system, which outperforms the state-of-the-art methods in room-level relocalization by 9.5% of PR-AUC and 7% of accuracy. In addition to exhaustive evaluation, we also carry out real-world tests, where AirLoc shows robustness in challenges like severe occlusion, perceptual aliasing, viewpoint shift, and deformation.

cs.CV↗