arXiv subjects

Yanhao Wang

Publications and source records attributed to Yanhao Wang.

At least 37 records · Page 2Linked to original sources

arXiv2024

Enhanced Multimodal RAG-LLM for Accurate Visual Question Answering

Multimodal large language models (MLLMs), such as GPT-4o, Gemini, LLaVA, and Flamingo, have made significant progress in integrating visual and textual modalities, excelling in tasks like visual question answering (VQA), image captioning, and content retrieval. They can generate coherent and contextually relevant descriptions of images. However, they still face challenges in accurately identifying and counting objects and determining their spatial locations, particularly in complex scenes with overlapping or small objects. To address these limitations, we propose a novel framework based on multimodal retrieval-augmented generation (RAG), which introduces structured scene graphs to enhance object recognition, relationship identification, and spatial understanding within images. Our framework improves the MLLM's capacity to handle tasks requiring precise visual descriptions, especially in scenarios with challenging perspectives, such as aerial views or scenes with dense object arrangements. Finally, we conduct extensive experiments on the VG-150 dataset that focuses on first-person visual understanding and the AUG dataset that involves aerial imagery. The results show that our approach consistently outperforms existing MLLMs in VQA tasks, which stands out in recognizing, localizing, and quantifying objects in different spatial contexts and provides more accurate visual descriptions.

cs.CV↗

arXiv2024

Low loss lumped-element inductors made from granular aluminum

Lumped-element inductors are an integral component in the circuit QED toolbox. However, it is challenging to build inductors that are simultaneously compact, linear and low-loss with standard approaches that either rely on the geometric inductance of superconducting thin films or on the kinetic inductance of Josephson junctions arrays. In this work, we overcome this challenge by utilizing the high kinetic inductance offered by superconducting granular aluminum (grAl). We demonstrate lumped-element inductors with a few nH of inductance that are up to $100$ times more compact than inductors built from pure aluminum (Al). To characterize the properties of these linear inductors, we first report on the performance of lumped-element resonators built entirely out of grAl with sheet inductances varying from $30-320\,$pH/sq and self-Kerr non-linearities of $0.2-20\,\mathrm{Hz/photon}$. Further, we demonstrate ex-situ integration of these grAl inductors into hybrid resonators with Al or tantalum (Ta) capacitor electrodes without increasing total internal losses. Interestingly, the measured internal quality factors systematically decrease with increasing room-temperature resistivity of the grAl film for all devices, indicating a trade-off between compactness and internal loss. For our lowest resistivity grAl films, we measure quality factors reaching $3.5 \times 10^6$ for the all-grAl devices and $4.5 \times 10^6$ for the hybrid grAl/Ta devices, similar to state-of-the-art quantum circuits. Our loss analysis suggests that the surface loss factor of grAl is similar to that of pure Al for our lowest resistivity films, while the increasing losses with resistivity could be explained by increasing conductor loss in the grAl film.

quant-ph↗

arXiv2024

FedMCP: Parameter-Efficient Federated Learning with Model-Contrastive Personalization

With increasing concerns and regulations on data privacy, fine-tuning pretrained language models (PLMs) in federated learning (FL) has become a common paradigm for NLP tasks. Despite being extensively studied, the existing methods for this problem still face two primary challenges. First, the huge number of parameters in large-scale PLMs leads to excessive communication and computational overhead. Second, the heterogeneity of data and tasks across clients poses a significant obstacle to achieving the desired fine-tuning performance. To address the above problems, we propose FedMCP, a novel parameter-efficient fine-tuning method with model-contrastive personalization for FL. Specifically, FedMCP adds two lightweight adapter modules, i.e., the global adapter and the private adapter, to the frozen PLMs within clients. In a communication round, each client sends only the global adapter to the server for federated aggregation. Furthermore, FedMCP introduces a model-contrastive regularization term between the two adapters. This, on the one hand, encourages the global adapter to assimilate universal knowledge and, on the other hand, the private adapter to capture client-specific knowledge. By leveraging both adapters, FedMCP can effectively provide fine-tuned personalized models tailored to individual clients. Extensive experiments on highly heterogeneous cross-task, cross-silo datasets show that FedMCP achieves substantial performance improvements over state-of-the-art FL fine-tuning approaches for PLMs.

cs.CL↗

arXiv2024

DPSW-Sketch: A Differentially Private Sketch Framework for Frequency Estimation over Sliding Windows (Technical Report)

The sliding window model of computation captures scenarios in which data are continually arriving in the form of a stream, and only the most recent $w$ items are used for analysis. In this setting, an algorithm needs to accurately track some desired statistics over the sliding window using a small space. When data streams contain sensitive information about individuals, the algorithm is also urgently needed to provide a provable guarantee of privacy. In this paper, we focus on the two fundamental problems of privately (1) estimating the frequency of an arbitrary item and (2) identifying the most frequent items (i.e., \emph{heavy hitters}), in the sliding window model. We propose \textsc{DPSW-Sketch}, a sliding window framework based on the count-min sketch that not only satisfies differential privacy over the stream but also approximates the results for frequency and heavy-hitter queries within bounded errors in sublinear time and space w.r.t.~$w$. Extensive experiments on five real-world and synthetic datasets show that \textsc{DPSW-Sketch} provides significantly better utility-privacy trade-offs than state-of-the-art methods.

cs.CR↗

arXiv2024

WaZI: A Learned and Workload-aware Z-Index

Learned indexes fit machine learning (ML) models to the data and use them to make query operations more time and space-efficient. Recent works propose using learned spatial indexes to improve spatial query performance by optimizing the storage layout or internal search structures according to the data distribution. However, only a few learned indexes exploit the query workload distribution to enhance their performance. In addition, building and updating learned spatial indexes are often costly on large datasets due to the inefficiency of (re)training ML models. In this paper, we present WaZI, a learned and workload-aware variant of the Z-index, which jointly optimizes the storage layout and search structures, as a viable solution for the above challenges of spatial indexing. Specifically, we first formulate a cost function to measure the performance of a Z-index on a dataset for a range-query workload. Then, we optimize the Z-index structure by minimizing the cost function through adaptive partitioning and ordering for index construction. Moreover, we design a novel page-skipping mechanism to improve the query performance of WaZI by reducing access to irrelevant data pages. Our extensive experiments show that the WaZI index improves range query time by 40% on average over the baselines while always performing better or comparably to state-of-the-art spatial indexes. Additionally, it also maintains good point query performance. Generally, WaZI provides favorable tradeoffs among query latency, construction time, and index size.

cs.DB↗

arXiv2024

Diversity-Aware $k$-Maximum Inner Product Search Revisited

The $k$-Maximum Inner Product Search ($k$MIPS) serves as a foundational component in recommender systems and various data mining tasks. However, while most existing $k$MIPS approaches prioritize the efficient retrieval of highly relevant items for users, they often neglect an equally pivotal facet of search results: \emph{diversity}. To bridge this gap, we revisit and refine the diversity-aware $k$MIPS (D$k$MIPS) problem by incorporating two well-known diversity objectives -- minimizing the average and maximum pairwise item similarities within the results -- into the original relevance objective. This enhancement, inspired by Maximal Marginal Relevance (MMR), offers users a controllable trade-off between relevance and diversity. We introduce \textsc{Greedy} and \textsc{DualGreedy}, two linear scan-based algorithms tailored for D$k$MIPS. They both achieve data-dependent approximations and, when aiming to minimize the average pairwise similarity, \textsc{DualGreedy} attains an approximation ratio of $1/4$ with an additive term for regularization. To further improve query efficiency, we integrate a lightweight Ball-Cone Tree (BC-Tree) index with the two algorithms. Finally, comprehensive experiments on ten real-world data sets demonstrate the efficacy of our proposed methods, showcasing their capability to efficiently deliver diverse and relevant search results to users.

cs.IR↗

arXiv2023

Sampling Algorithms for Butterfly Counting on Temporal Bipartite Graphs

Temporal bipartite graphs are widely used to denote time-evolving relationships between two disjoint sets of nodes, such as customer-product interactions in E-commerce and user-group memberships in social networks. Temporal butterflies, $(2,2)$-bicliques that occur within a short period and in a prescribed order, are essential in modeling the structural and sequential patterns of such graphs. Counting the number of temporal butterflies is thus a fundamental task in analyzing temporal bipartite graphs. However, existing algorithms for butterfly counting on static bipartite graphs and motif counting on temporal unipartite graphs are inefficient for this purpose. In this paper, we present a general framework with three sampling strategies for temporal butterfly counting. Since exact counting can be time-consuming on large graphs, our approach alternatively computes approximate estimates accurately and efficiently. We also provide analytical bounds on the number of samples each strategy requires to obtain estimates with small relative errors and high probability. We finally evaluate our framework on six real-world datasets and demonstrate its superior accuracy and efficiency compared to several baselines. Overall, our proposed framework and sampling strategies provide efficient and accurate approaches to approximating temporal butterfly counts on large-scale temporal bipartite graphs.

cs.SI↗

arXiv2023

Surpassing millisecond coherence times in on-chip superconducting quantum memories by optimizing materials, processes, and circuit design

The performance of superconducting quantum circuits for quantum computing has advanced tremendously in recent decades; however, a comprehensive understanding of relaxation mechanisms does not yet exist. In this work, we utilize a multimode approach to characterizing energy losses in superconducting quantum circuits, with the goals of predicting device performance and improving coherence through materials, process, and circuit design optimization. Using this approach, we measure significant reductions in surface and bulk dielectric losses by employing a tantalum-based materials platform and annealed sapphire substrates. With this knowledge we predict and experimentally verify the relaxation times of aluminum- and tantalum-based transmon qubits. We additionally optimize device geometry to maximize coherence within a coaxial tunnel architecture, and realize on-chip quantum memories with single-photon Ramsey times of 2.0$-$2.7 ms, limited by their energy relaxation times of 1.0$-$1.4 ms. To our knowledge this is the highest coherence achieved in an on-chip quantum memory, and demonstrates an advancement towards a more modular and compact coaxial circuit architecture for bosonic qubits with reproducibly high coherence.

quant-ph↗

arXiv2023

Spectral Normalized-Cut Graph Partitioning with Fairness Constraints

Normalized-cut graph partitioning aims to divide the set of nodes in a graph into $k$ disjoint clusters to minimize the fraction of the total edges between any cluster and all other clusters. In this paper, we consider a fair variant of the partitioning problem wherein nodes are characterized by a categorical sensitive attribute (e.g., gender or race) indicating membership to different demographic groups. Our goal is to ensure that each group is approximately proportionally represented in each cluster while minimizing the normalized cut value. To resolve this problem, we propose a two-phase spectral algorithm called FNM. In the first phase, we add an augmented Lagrangian term based on our fairness criteria to the objective function for obtaining a fairer spectral node embedding. Then, in the second phase, we design a rounding scheme to produce $k$ clusters from the fair embedding that effectively trades off fairness and partition quality. Through comprehensive experiments on nine benchmark datasets, we demonstrate the superior performance of FNM compared with three baseline methods.

cs.LG↗

arXiv2023

Balancing Utility and Fairness in Submodular Maximization (Technical Report)

Submodular function maximization is a fundamental combinatorial optimization problem with plenty of applications -- including data summarization, influence maximization, and recommendation. In many of these problems, the goal is to find a solution that maximizes the average utility over all users, for each of whom the utility is defined by a monotone submodular function. However, when the population of users is composed of several demographic groups, another critical problem is whether the utility is fairly distributed across different groups. Although the \emph{utility} and \emph{fairness} objectives are both desirable, they might contradict each other, and, to the best of our knowledge, little attention has been paid to optimizing them jointly. To fill this gap, we propose a new problem called \emph{Bicriteria Submodular Maximization} (BSM) to balance utility and fairness. Specifically, it requires finding a fixed-size solution to maximize the utility function, subject to the value of the fairness function not being below a threshold. Since BSM is inapproximable within any constant factor, we focus on designing efficient instance-dependent approximation schemes. Our algorithmic proposal comprises two methods, with different approximation factors, obtained by converting a BSM instance into other submodular optimization problem instances. Using real-world and synthetic datasets, we showcase applications of our proposed methods in three submodular maximization problems: maximum coverage, influence maximization, and facility location.

cs.DS↗

arXiv2023

A Customized Text Sanitization Mechanism with Differential Privacy

As privacy issues are receiving increasing attention within the Natural Language Processing (NLP) community, numerous methods have been proposed to sanitize texts subject to differential privacy. However, the state-of-the-art text sanitization mechanisms based on metric local differential privacy (MLDP) do not apply to non-metric semantic similarity measures and cannot achieve good trade-offs between privacy and utility. To address the above limitations, we propose a novel Customized Text (CusText) sanitization mechanism based on the original $ε$-differential privacy (DP) definition, which is compatible with any similarity measure. Furthermore, CusText assigns each input token a customized output set of tokens to provide more advanced privacy protection at the token level. Extensive experiments on several benchmark datasets show that CusText achieves a better trade-off between privacy and utility than existing mechanisms. The code is available at https://github.com/sai4july/CusText.

cs.CR↗

arXiv2023

Opinion-aware Influence Maximization in Online Social Networks

Influence maximization (IM) aims to find seed users on an online social network to maximize the spread of information about a target product through word-of-mouth propagation among all users. Prior IM methods mostly focus on maximizing the overall influence spread, which assumes that all users are potential customers of the product and that more exposure leads to higher benefits. However, in real-world scenarios, some users who dislike the product may express and spread negative opinions, damaging the product's reputation and lowering its profit. This paper investigates the opinion-aware influence maximization (OIM) problem, which finds a set of seed users to maximize the positive opinions toward the product while minimizing the negative opinions. We propose a novel algorithm for the OIM problem. Specifically, after obtaining the users with positive and negative opinions towards the product from historical data, we design a reverse reachable set-based method for opinion-aware influence estimation and a sandwich approximation algorithm for seed set selection. Despite the NP-hardness and non-submodularity of OIM, our algorithm achieves a data-dependent approximation factor for OIM. Experimental results on three real-world datasets demonstrate that our algorithm improves the spread of positive opinions while reducing the spread of negative opinions compared to existing methods.

cs.SI↗

arXiv2023

Max-Min Diversification with Fairness Constraints: Exact and Approximation Algorithms

Diversity maximization aims to select a diverse and representative subset of items from a large dataset. It is a fundamental optimization task that finds applications in data summarization, feature selection, web search, recommender systems, and elsewhere. However, in a setting where data items are associated with different groups according to sensitive attributes like sex or race, it is possible that algorithmic solutions for this task, if left unchecked, will under- or over-represent some of the groups. Therefore, we are motivated to address the problem of \emph{max-min diversification with fairness constraints}, aiming to select $k$ items to maximize the minimum distance between any pair of selected items while ensuring that the number of items selected from each group falls within predefined lower and upper bounds. In this work, we propose an exact algorithm based on integer linear programming that is suitable for small datasets as well as a $\frac{1-\varepsilon}{5}$-approximation algorithm for any $\varepsilon \in (0, 1)$ that scales to large datasets. Extensive experiments on real-world datasets demonstrate the superior performance of our proposed algorithms over existing ones.

cs.DS↗

arXiv2022

SAH: Shifting-aware Asymmetric Hashing for Reverse $k$-Maximum Inner Product Search

This paper investigates a new yet challenging problem called Reverse $k$-Maximum Inner Product Search (R$k$MIPS). Given a query (item) vector, a set of item vectors, and a set of user vectors, the problem of R$k$MIPS aims to find a set of user vectors whose inner products with the query vector are one of the $k$ largest among the query and item vectors. We propose the first subquadratic-time algorithm, i.e., Shifting-aware Asymmetric Hashing (SAH), to tackle the R$k$MIPS problem. To speed up the Maximum Inner Product Search (MIPS) on item vectors, we design a shifting-invariant asymmetric transformation and develop a novel sublinear-time Shifting-Aware Asymmetric Locality Sensitive Hashing (SA-ALSH) scheme. Furthermore, we devise a new blocking strategy based on the Cone-Tree to effectively prune user vectors (in a batch). We prove that SAH achieves a theoretical guarantee for solving the RMIPS problem. Experimental results on five real-world datasets show that SAH runs 4$\sim$8$\times$ faster than the state-of-the-art methods for R$k$MIPS while achieving F1-scores of over 90\%. The code is available at \url{https://github.com/HuangQiang/SAH}.

cs.IR↗

arXiv2022

Efficient Sampling Algorithms for Approximate Motif Counting in Temporal Graph Streams

A great variety of complex systems, from user interactions in communication networks to transactions in financial markets, can be modeled as temporal graphs consisting of a set of vertices and a series of timestamped and directed edges. Temporal motifs are generalized from subgraph patterns in static graphs which consider edge orderings and durations in addition to topologies. Counting the number of occurrences of temporal motifs is a fundamental problem for temporal network analysis. However, existing methods either cannot support temporal motifs or suffer from performance issues. Moreover, they cannot work in the streaming model where edges are observed incrementally over time. In this paper, we focus on approximate temporal motif counting via random sampling. We first propose two sampling algorithms for temporal motif counting in the offline setting. The first is an edge sampling (ES) algorithm for estimating the number of instances of any temporal motif. The second is an improved edge-wedge sampling (EWS) algorithm that hybridizes edge sampling with wedge sampling for counting temporal motifs with $3$ vertices and $3$ edges. Furthermore, we propose two algorithms to count temporal motifs incrementally in temporal graph streams by extending the ES and EWS algorithms referred to as SES and SEWS. We provide comprehensive analyses of the theoretical bounds and complexities of our proposed algorithms. Finally, we perform extensive experimental evaluations of our proposed algorithms on several real-world temporal graphs. The results show that ES and EWS have higher efficiency, better accuracy, and greater scalability than state-of-the-art sampling methods for temporal motif counting in the offline setting. Moreover, SES and SEWS achieve up to three orders of magnitude speedups over ES and EWS while having comparable estimation errors for temporal motif counting in the streaming setting.

cs.SI↗

arXiv2022

Graph Summarization via Node Grouping: A Spectral Algorithm

Graph summarization via node grouping is a popular method to build concise graph representations by grouping nodes from the original graph into supernodes and encoding edges into superedges such that the loss of adjacency information is minimized. Such summaries have immense applications in large-scale graph analytics due to their small size and high query processing efficiency. In this paper, we reformulate the loss minimization problem for summarization into an equivalent integer maximization problem. By initially allowing relaxed (fractional) solutions for integer maximization, we analytically expose the underlying connections to the spectral properties of the adjacency matrix. Consequently, we design an algorithm called SpecSumm that consists of two phases. In the first phase, motivated by spectral graph theory, we apply k-means clustering on the k largest (in magnitude) eigenvectors of the adjacency matrix to assign nodes to supernodes. In the second phase, we propose a greedy heuristic that updates the initial assignment to further improve summary quality. Finally, via extensive experiments on 11 datasets, we show that SpecSumm efficiently produces high-quality summaries compared to state-of-the-art summarization algorithms and scales to graphs with millions of nodes.

cs.SI↗

arXiv2022

Happiness Maximizing Sets under Group Fairness Constraints (Technical Report)

Finding a happiness maximizing set (HMS) from a database, i.e., selecting a small subset of tuples that preserves the best score with respect to any nonnegative linear utility function, is an important problem in multi-criteria decision-making. When an HMS is extracted from a set of individuals to assist data-driven algorithmic decisions such as hiring and admission, it is crucial to ensure that the HMS can fairly represent different groups of candidates without bias and discrimination. However, although the HMS problem was extensively studied in the database community, existing algorithms do not take group fairness into account and may provide solutions that under-represent some groups. In this paper, we propose and investigate a fair variant of HMS (FairHMS) that not only maximizes the minimum happiness ratio but also guarantees that the number of tuples chosen from each group falls within predefined lower and upper bounds. Similar to the vanilla HMS problem, we show that FairHMS is NP-hard in three and higher dimensions. Therefore, we first propose an exact interval cover-based algorithm called IntCov for FairHMS on two-dimensional databases. Then, we propose a bicriteria approximation algorithm called BiGreedy for FairHMS on multi-dimensional databases by transforming it into a submodular maximization problem under a matroid constraint. We also design an adaptive sampling strategy to improve the practical efficiency of BiGreedy. Extensive experiments on real-world and synthetic datasets confirm the efficacy and efficiency of our proposal.

cs.DB↗

arXiv2022

Streaming Algorithms for Diversity Maximization with Fairness Constraints

Diversity maximization is a fundamental problem with wide applications in data summarization, web search, and recommender systems. Given a set $X$ of $n$ elements, it asks to select a subset $S$ of $k \ll n$ elements with maximum \emph{diversity}, as quantified by the dissimilarities among the elements in $S$. In this paper, we focus on the diversity maximization problem with fairness constraints in the streaming setting. Specifically, we consider the max-min diversity objective, which selects a subset $S$ that maximizes the minimum distance (dissimilarity) between any pair of distinct elements within it. Assuming that the set $X$ is partitioned into $m$ disjoint groups by some sensitive attribute, e.g., sex or race, ensuring \emph{fairness} requires that the selected subset $S$ contains $k_i$ elements from each group $i \in [1,m]$. A streaming algorithm should process $X$ sequentially in one pass and return a subset with maximum \emph{diversity} while guaranteeing the fairness constraint. Although diversity maximization has been extensively studied, the only known algorithms that can work with the max-min diversity objective and fairness constraints are very inefficient for data streams. Since diversity maximization is NP-hard in general, we propose two approximation algorithms for fair diversity maximization in data streams, the first of which is $\frac{1-\varepsilon}{4}$-approximate and specific for $m=2$, where $\varepsilon \in (0,1)$, and the second of which achieves a $\frac{1-\varepsilon}{3m+2}$-approximation for an arbitrary $m$. Experimental results on real-world and synthetic datasets show that both algorithms provide solutions of comparable quality to the state-of-the-art algorithms while running several orders of magnitude faster in the streaming setting.

cs.DS↗