arXiv subjects

Jeffrey Xu Yu

Publications and source records attributed to Jeffrey Xu Yu.

At least 37 records · Page 2Linked to original sources

arXiv2024

Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems

Recent advancements in large language model (LLM)-powered agents have shown that collective intelligence can significantly outperform individual capabilities, largely attributed to the meticulously designed inter-agent communication topologies. Though impressive in performance, existing multi-agent pipelines inherently introduce substantial token overhead, as well as increased economic costs, which pose challenges for their large-scale deployments. In response to this challenge, we propose an economical, simple, and robust multi-agent communication framework, termed $\texttt{AgentPrune}$, which can seamlessly integrate into mainstream multi-agent systems and prunes redundant or even malicious communication messages. Technically, $\texttt{AgentPrune}$ is the first to identify and formally define the \textit{communication redundancy} issue present in current LLM-based multi-agent pipelines, and efficiently performs one-shot pruning on the spatial-temporal message-passing graph, yielding a token-economic and high-performing communication topology. Extensive experiments across six benchmarks demonstrate that $\texttt{AgentPrune}$ \textbf{(I)} achieves comparable results as state-of-the-art topologies at merely $\$5.6$ cost compared to their $\$43.7$, \textbf{(II)} integrates seamlessly into existing multi-agent frameworks with $28.1\%\sim72.8\%\downarrow$ token reduction, and \textbf{(III)} successfully defend against two types of agent-based adversarial attacks with $3.5\%\sim10.8\%\uparrow$ performance boost.

cs.MA↗

arXiv2024

Beyond Efficiency: Molecular Data Pruning for Enhanced Generalization

With the emergence of various molecular tasks and massive datasets, how to perform efficient training has become an urgent yet under-explored issue in the area. Data pruning (DP), as an oft-stated approach to saving training burdens, filters out less influential samples to form a coreset for training. However, the increasing reliance on pretrained models for molecular tasks renders traditional in-domain DP methods incompatible. Therefore, we propose a Molecular data Pruning framework for enhanced Generalization (MolPeg), which focuses on the source-free data pruning scenario, where data pruning is applied with pretrained models. By maintaining two models with different updating paces during training, we introduce a novel scoring function to measure the informativeness of samples based on the loss discrepancy. As a plug-and-play framework, MolPeg realizes the perception of both source and target domain and consistently outperforms existing DP methods across four downstream tasks. Remarkably, it can surpass the performance obtained from full-dataset training, even when pruning up to 60-70% of the data on HIV and PCBA dataset. Our work suggests that the discovery of effective data-pruning metrics could provide a viable path to both enhanced efficiency and superior generalization in transfer learning.

cs.LG↗

arXiv2024

Rethinking Fair Graph Neural Networks from Re-balancing

Driven by the powerful representation ability of Graph Neural Networks (GNNs), plentiful GNN models have been widely deployed in many real-world applications. Nevertheless, due to distribution disparities between different demographic groups, fairness in high-stake decision-making systems is receiving increasing attention. Although lots of recent works devoted to improving the fairness of GNNs and achieved considerable success, they all require significant architectural changes or additional loss functions requiring more hyper-parameter tuning. Surprisingly, we find that simple re-balancing methods can easily match or surpass existing fair GNN methods. We claim that the imbalance across different demographic groups is a significant source of unfairness, resulting in imbalanced contributions from each group to the parameters updating. However, these simple re-balancing methods have their own shortcomings during training. In this paper, we propose FairGB, Fair Graph Neural Network via re-Balancing, which mitigates the unfairness of GNNs by group balancing. Technically, FairGB consists of two modules: counterfactual node mixup and contribution alignment loss. Firstly, we select counterfactual pairs across inter-domain and inter-class, and interpolate the ego-networks to generate new samples. Guided by analysis, we can reveal the debiasing mechanism of our model by the causal view and prove that our strategy can make sensitive attributes statistically independent from target labels. Secondly, we reweigh the contribution of each group according to gradients. By combining these two modules, they can mutually promote each other. Experimental results on benchmark datasets show that our method can achieve state-of-the-art results concerning both utility and fairness metrics. Code is available at https://github.com/ZhixunLEE/FairGB.

cs.LG↗

arXiv2024

Fast Iterative Graph Computing with Updated Neighbor States

Enhancing the efficiency of iterative computation on graphs has garnered considerable attention in both industry and academia. Nonetheless, the majority of efforts focus on expediting iterative computation by minimizing the running time per iteration step, ignoring the optimization of the number of iteration rounds, which is a crucial aspect of iterative computation. We experimentally verified the correlation between the vertex processing order and the number of iterative rounds, thus making it possible to reduce the number of execution rounds for iterative computation. In this paper, we propose a graph reordering method, GoGraph, which can construct a well-formed vertex processing order effectively reducing the number of iteration rounds and, consequently, accelerating iterative computation. Before delving into GoGraph, a metric function is introduced to quantify the efficiency of vertex processing order in accelerating iterative computation. This metric reflects the quality of the processing order by counting the number of edges whose source precedes the destination. GoGraph employs a divide-and-conquer mindset to establish the vertex processing order by maximizing the value of the metric function. Our experimental results show that GoGraph outperforms current state-of-the-art reordering algorithms by 1.83x on average (up to 3.34x) in runtime.

cs.DC↗

arXiv2024

ZeroG: Investigating Cross-dataset Zero-shot Transferability in Graphs

With the development of foundation models such as large language models, zero-shot transfer learning has become increasingly significant. This is highlighted by the generative capabilities of NLP models like GPT-4, and the retrieval-based approaches of CV models like CLIP, both of which effectively bridge the gap between seen and unseen data. In the realm of graph learning, the continuous emergence of new graphs and the challenges of human labeling also amplify the necessity for zero-shot transfer learning, driving the exploration of approaches that can generalize across diverse graph data without necessitating dataset-specific and label-specific fine-tuning. In this study, we extend such paradigms to zero-shot transferability in graphs by introducing ZeroG, a new framework tailored to enable cross-dataset generalization. Addressing the inherent challenges such as feature misalignment, mismatched label spaces, and negative transfer, we leverage a language model to encode both node attributes and class semantics, ensuring consistent feature dimensions across datasets. We also propose a prompt-based subgraph sampling module that enriches the semantic information and structure information of extracted subgraphs using prompting nodes and neighborhood aggregation, respectively. We further adopt a lightweight fine-tuning strategy that reduces the risk of overfitting and maintains the zero-shot learning efficacy of the language model. The results underscore the effectiveness of our model in achieving significant cross-dataset zero-shot transferability, opening pathways for the development of graph foundation models. Codes and data are available at https://github.com/NineAbyss/ZeroG.

cs.LG↗

arXiv2024

A Survey of Graph Meets Large Language Model: Progress and Future Directions

Graph plays a significant role in representing and analyzing complex relationships in real-world applications such as citation networks, social networks, and biological data. Recently, Large Language Models (LLMs), which have achieved tremendous success in various domains, have also been leveraged in graph-related tasks to surpass traditional Graph Neural Networks (GNNs) based methods and yield state-of-the-art performance. In this survey, we first present a comprehensive review and analysis of existing methods that integrate LLMs with graphs. First of all, we propose a new taxonomy, which organizes existing methods into three categories based on the role (i.e., enhancer, predictor, and alignment component) played by LLMs in graph-related tasks. Then we systematically survey the representative methods along the three categories of the taxonomy. Finally, we discuss the remaining limitations of existing studies and highlight promising avenues for future research. The relevant papers are summarized and will be consistently updated at: https://github.com/yhLeeee/Awesome-LLMs-in-Graph-tasks.

cs.LG↗

arXiv2023

A Unified and Scalable Algorithm Framework of User-Defined Temporal $(k,\mathcal{X})$-Core Query

Querying cohesive subgraphs on temporal graphs (e.g., social network, finance network, etc.) with various conditions has attracted intensive research interests recently. In this paper, we study a novel Temporal $(k,\mathcal{X})$-Core Query (TXCQ) that extends a fundamental Temporal $k$-Core Query (TCQ) proposed in our conference paper by optimizing or constraining an arbitrary metric $\mathcal{X}$ of $k$-core, such as size, engagement, interaction frequency, time span, burstiness, periodicity, etc. Our objective is to address specific TXCQ instances with conditions on different $\mathcal{X}$ in a unified algorithm framework that guarantees scalability. For that, this journal paper proposes a taxonomy of measurement $\mathcal{X}(\cdot)$ and achieve our objective using a two-phase framework while $\mathcal{X}(\cdot)$ is time-insensitive or time-monotonic. Specifically, Phase 1 still leverages the query processing algorithm of TCQ to induce all distinct $k$-cores during a given time range, and meanwhile locates the ``time zones'' in which the cores emerge. Then, Phase 2 conducts fast local search and $\mathcal{X}$ evaluation in each time zone with respect to the time insensitivity or monotonicity of $\mathcal{X}(\cdot)$. By revealing two insightful concepts named tightest time interval and loosest time interval that bound time zones, the redundant core induction and unnecessary $\mathcal{X}$ evaluation in a zone can be reduced dramatically. Our experimental results demonstrate that TXCQ can be addressed as efficiently as TCQ, which achieves the latest state-of-the-art performance, by using a general algorithm framework that leaves $\mathcal{X}(\cdot)$ as a user-defined function.

cs.DB↗

arXiv2023

GSLB: The Graph Structure Learning Benchmark

Graph Structure Learning (GSL) has recently garnered considerable attention due to its ability to optimize both the parameters of Graph Neural Networks (GNNs) and the computation graph structure simultaneously. Despite the proliferation of GSL methods developed in recent years, there is no standard experimental setting or fair comparison for performance evaluation, which creates a great obstacle to understanding the progress in this field. To fill this gap, we systematically analyze the performance of GSL in different scenarios and develop a comprehensive Graph Structure Learning Benchmark (GSLB) curated from 20 diverse graph datasets and 16 distinct GSL algorithms. Specifically, GSLB systematically investigates the characteristics of GSL in terms of three dimensions: effectiveness, robustness, and complexity. We comprehensively evaluate state-of-the-art GSL algorithms in node- and graph-level tasks, and analyze their performance in robust learning and model complexity. Further, to facilitate reproducible research, we have developed an easy-to-use library for training, evaluating, and visualizing different GSL methods. Empirical results of our extensive experiments demonstrate the ability of GSL and reveal its potential benefits on various downstream tasks, offering insights and opportunities for future research. The code of GSLB is available at: https://github.com/GSL-Benchmark/GSLB.

cs.LG↗

arXiv2023

Scalable Time-Range k-Core Query on Temporal Graphs(Full Version)

Querying cohesive subgraphs on temporal graphs with various time constraints has attracted intensive research interests recently. In this paper, we study a novel Temporal k-Core Query (TCQ) problem: given a time interval, find all distinct k-cores that exist within any subintervals from a temporal graph, which generalizes the previous historical k-core query. This problem is challenging because the number of subintervals increases quadratically to the span of time interval. For that, we propose a novel Temporal Core Decomposition (TCD) algorithm that decrementally induces temporal k-cores from the previously induced ones and thus reduces "intra-core" redundant computation significantly. Then, we introduce an intuitive concept named Tightest Time Interval (TTI) for temporal k-core, and design an optimization technique with theoretical guarantee that leverages TTI as a key to predict which subintervals will induce duplicated k-cores and prunes the subintervals completely in advance, thereby eliminating "inter-core" redundant computation. The complexity of optimized TCD (OTCD) algorithm no longer depends on the span of query time interval but only the scale of final results, which means OTCD algorithm is scalable. Moreover, we propose a compact in-memory data structure named Temporal Edge List (TEL) to implement OTCD algorithm efficiently in physical level with bounded memory requirement. TEL organizes temporal edges in a "timeline" and can be updated instantly when new edges arrive, and thus our approach can also deal with dynamic temporal graphs. We compare OTCD algorithm with the incremental historical k-core query on several real-world temporal graphs, and observe that OTCD algorithm outperforms it by three orders of magnitude, even though OTCD algorithm needs none precomputed index.

cs.DB↗

arXiv2022

PSPC: Efficient Parallel Shortest Path Counting on Large-Scale Graphs

In modern graph analytics, the shortest path is a fundamental concept. Numerous \rrev{recent works} concentrate mostly on the distance of these shortest paths. Nevertheless, in the era of betweenness analysis, the counting of the shortest path between $s$ and $t$ is equally crucial. \rrev{It} is \rev{also} an important issue in the area of graph databases. In recent years, several studies have been conducted in an effort to tackle such issues. Nonetheless, the present technique faces a considerable barrier to parallel due to the dependencies in the index construction stage, hence limiting its application possibilities and wasting the potential hardware performance. To address this problem, we provide a parallel shortest path counting method that could avoid these dependencies and obtain approximately linear index time speedup as the number of threads increases. Our empirical evaluations verify the efficiency and effectiveness.

cs.DB↗

arXiv2022

Finding Top-r Influential Communities under Aggregation Functions

Community search is a problem that seeks cohesive and connected subgraphs in a graph that satisfy certain topology constraints, e.g., degree constraints. The majority of existing works focus exclusively on the topology and ignore the nodes' influence in the communities. To tackle this deficiency, influential community search is further proposed to include the node's influence. Each node has a weight, namely influence value, in the influential community search problem to represent its network influence. The influence value of a community is produced by an aggregated function, e.g., max, min, avg, and sum, over the influence values of the nodes in the same community. The objective of the influential community search problem is to locate the top-r communities with the highest influence values while satisfying the topology constraints. Existing studies on influential community search have several limitations: (i) they focus exclusively on simple aggregation functions such as min, which may fall short of certain requirements in many real-world scenarios, and (ii) they impose no limitation on the size of the community, whereas most real-world scenarios do. This motivates us to conduct a new study to fill this gap. We consider the problem of identifying the top-r influential communities with/without size constraints while using more complicated aggregation functions such as sum or avg. We give a theoretical analysis demonstrating the hardness of the problems and propose efficient and effective heuristic solutions for our topr influential community search problems. Extensive experiments on real large graphs demonstrate that our proposed solution is significantly more efficient than baseline solutions.

cs.SI↗

arXiv2021

Uncertainty-aware Cardinality Estimation by Neural Network Gaussian Process

Deep Learning (DL) has achieved great success in many real applications. Despite its success, there are some main problems when deploying advanced DL models in database systems, such as hyper-parameters tuning, the risk of overfitting, and lack of prediction uncertainty. In this paper, we study cardinality estimation for SQL queries with a focus on uncertainty, which we believe is important in database systems when dealing with a large number of user queries on various applications. With uncertainty ensured, instead of trusting an estimator learned as it is, a query optimizer can explore other options when the estimator learned has a large variance, and it also becomes possible to update the estimator to improve its prediction in areas with high uncertainty. The approach we explore is different from the direction of deploying sophisticated DL models in database systems to build cardinality estimators. We employ Bayesian deep learning (BDL), which serves as a bridge between Bayesian inference and deep learning.The prediction distribution by BDL provides principled uncertainty calibration for the prediction. In addition, when the network width of a BDL model goes to infinity, the model performs equivalent to Gaussian Process (GP). This special class of BDL, known as Neural Network Gaussian Process (NNGP), inherits the advantages of Bayesian approach while keeping universal approximation of neural network, and can utilize a much larger model space to model distribution-free data as a nonparametric model. We show that our uncertainty-aware NNGP estimator achieves high accuracy, can be built very fast, and is robust to query workload shift, in our extensive performance studies by comparing with the existing approaches.

cs.DB↗

arXiv2021

Towards Feature-free TSP Solver Selection: A Deep Learning Approach

The Travelling Salesman Problem (TSP) is a classical NP-hard problem and has broad applications in many disciplines and industries. In a large scale location-based services system, users issue TSP queries concurrently, where a TSP query is a TSP instance with $n$ points. In the literature, many advanced TSP solvers are developed to find high-quality solutions. Such solvers can solve some TSP instances efficiently but may take an extremely long time for some other instances. Due to the diversity of TSP instances, it is well-known that there exists no universal best solver dominating all other solvers on all possible TSP instances. To solve TSP efficiently, in addition to developing new TSP solvers, it needs to find a per-instance solver for each TSP instance, which is known as the TSP solver selection problem. In this paper, for the first time, we propose a deep learning framework, \CTAS, for TSP solver selection in an end-to-end manner. Specifically, \CTAS exploits deep convolutional neural networks to extract informative features from TSP instances and involves data argumentation strategies to handle the scarcity of labeled TSP instances. Moreover, to support large scale TSP solver selection, we construct a challenging TSP benchmark dataset with 6,000 instances, which is known as the largest TSP benchmark. Our \CTAS achieves over 2$\times$ speedup of the average running time, comparing the single best solver, and outperforms the state-of-the-art statistical models.

cs.AI↗

arXiv2021

Fast Distributed Complex Join Processing

In this work, we study the problem of co-optimize communication, pre-computing, and computation cost in one-round multi-way join evaluation. We propose a multi-way join approach ADJ (Adaptive Distributed Join) for complex join which finds one optimal query plan to process by exploring cost-effective partial results in terms of the trade-off between pre-computing, communication, and computation.We analyze the input relations for a given join query and find one optimal over a set of query plans in some specific form, with high-quality cost estimation by sampling. Our extensive experiments confirm that ADJ outperforms the existing multi-way join methods by up to orders of magnitude.

cs.DB↗

arXiv2021

Towards Expectation-Maximization by SQL in RDBMS

Integrating machine learning techniques into RDBMSs is an important task since there are many real applications that require modeling (e.g., business intelligence, strategic analysis) as well as querying data in RDBMSs. In this paper, we provide an SQL solution that has the potential to support different machine learning modelings. As an example, we study how to support unsupervised probabilistic modeling, that has a wide range of applications in clustering, density estimation and data summarization, and focus on Expectation-Maximization (EM) algorithms, which is a general technique for finding maximum likelihood estimators. To train a model by EM, it needs to update the model parameters by an E-step and an M-step in a while-loop iteratively until it converges to a level controled by some threshold or repeats a certain number of iterations. To support EM in RDBMSs, we show our answers to the matrix/vectors representations in RDBMSs, the relational algebra operations to support the linear algebra operations required by EM, parameters update by relational algebra, and the support of a while-loop. It is important to note that the SQL'99 recursion cannot be used to handle such a while-loop since the M-step is non-monotonic. In addition, assume that a model has been trained by an EM algorithm, we further design an automatic in-database model maintenance mechanism to maintain the model when the underlying training data changes.We have conducted experimental studies and will report our findings in this paper.

cs.DB↗

arXiv2020

Joint Embedding in Named Entity Linking on Sentence Level

Named entity linking is to map an ambiguous mention in documents to an entity in a knowledge base. The named entity linking is challenging, given the fact that there are multiple candidate entities for a mention in a document. It is difficult to link a mention when it appears multiple times in a document, since there are conflicts by the contexts around the appearances of the mention. In addition, it is difficult since the given training dataset is small due to the reason that it is done manually to link a mention to its mapping entity. In the literature, there are many reported studies among which the recent embedding methods learn vectors of entities from the training dataset at document level. To address these issues, we focus on how to link entity for mentions at a sentence level, which reduces the noises introduced by different appearances of the same mention in a document at the expense of insufficient information to be used. We propose a new unified embedding method by maximizing the relationships learned from knowledge graphs. We confirm the effectiveness of our method in our experimental studies.

cs.CL↗

arXiv2020

Graph Ordering: Towards the Optimal by Learning

Graph representation learning has achieved a remarkable success in many graph-based applications, such as node classification, link prediction, and community detection. These models are usually designed to preserve the vertex information at different granularity and reduce the problems in discrete space to some machine learning tasks in continuous space. However, regardless of the fruitful progress, for some kind of graph applications, such as graph compression and edge partition, it is very hard to reduce them to some graph representation learning tasks. Moreover, these problems are closely related to reformulating a global layout for a specific graph, which is an important NP-hard combinatorial optimization problem: graph ordering. In this paper, we propose to attack the graph ordering problem behind such applications by a novel learning approach. Distinguished from greedy algorithms based on predefined heuristics, we propose a neural network model: Deep Order Network (DON) to capture the hidden locality structure from partial vertex order sets. Supervised by sampled partial order, DON has the ability to infer unseen combinations. Furthermore, to alleviate the combinatorial explosion in the training space of DON and make the efficient partial vertex order sampling , we employ a reinforcement learning model: the Policy Network, to adjust the partial order sampling probabilities during the training phase of DON automatically. To this end, the Policy Network can improve the training efficiency and guide DON to evolve towards a more effective model automatically. Comprehensive experiments on both synthetic and real data validate that DON-RL outperforms the current state-of-the-art heuristic algorithm consistently. Two case studies on graph compression and edge partitioning demonstrate the potential power of DON-RL in real applications.

cs.SI↗

arXiv2019

Graph Iso/Auto-morphism: A Divide-&-Conquer Approach

The graph isomorphism is to determine whether two graphs are isomorphic. A closely related problem is automorphism detection, where an isomorphism between two graphs is a bijection between their vertex sets that preserves adjacency, and an automorphism is an isomorphism from a graph to itself. Applications of graph isomorphism/automorphism include database indexing, network simplification, network anonymization. By graph automorphism, we deal with symmetric subgraph matching (SSM), which is to find all subgraphs that are symmetric to a given subgraph in G. An application of SSM is to identify multiple seed sets that have the same influence power as a seed set found by influence maximization in a social network. To test two graphs for isomorphism, canonical labeling has been studied to relabel a graph in such a way that isomorphic graphs are identical after relabeling. Efficient canonical labeling algorithms have been designed by individualization-refinement. They enumerate all permutations using a search tree, and select the minimum as the canonical labeling, which prunes candidates during enumeration. Despite high performance in benchmark graphs, these algorithms face difficulties in handling massive graphs. In this paper, we design a new efficient canonical labeling algorithm DviCL. Different from previous algorithms, we take a divide-&-conquer approach to partition G. By partitioning G, an AutoTree is constructed, which preserves symmetric structures and the automorphism group of G. The canonical labeling for a tree node can be obtained by the canonical labeling of its child nodes, and the canonical labeling for the root is the one for G. Such AutoTree can also be effectively used to answer the automorphism group, symmetric subgraphs. We conducted extensive performance studies using 22 large graphs, and confirmed that DviCL is much more efficient and robust than the state-of-the-art.

cs.SI↗