Xin Huang

Wenbo Shang, Xuliang Zhu, Xin Huang

Unified graph representation learning aims to generate node embeddings, which can be applied to multiple downstream applications of graph analytics. However, existing studies based on graph neural networks and language models either suffer from the limitations of numerous training needs toward specific downstream predictions, poor generalization, or shallow semantic features. In this work, we propose a novel Path-LLM model to efficiently learn unified graph representation, which leverages a powerful large language model (LLM) to incorporate our proposed path features. Our Path-LLM framework consists of four well-designed techniques. First, we develop a new mechanism of long-to-short shortest path (L2SP) selection, which can cover key connections between different dense groups. An in-depth analysis and comparison of different path selections is conducted to justify the rationale behind our designed L2SP method. Next, we design path textualization to obtain L2SP-based training texts with key phrase selection from node text attributes. We then feed the texts into a self-supervised LLM training process to align next node/edge generation in L2SP with next token generation in causal language modeling for graph representation learning and finally extract the unified graph embeddings. We theoretically analyze the algorithm complexity of our Path-LLM approach. Extensive experiments on large-scale graph benchmarks validate the superiority of Path-LLM against state-of-the-art methods WalkLM, GraphGPT, OFA, and GraphTranslator on two classical graph learning tasks (node classification and edge validation) and one NP-hard graph query processing task (keyword search). Compared with WalkLM, our approach saves more than 90% of training paths on millions-scale graphs and runs at most 35x faster.

Yi Xu, Yuxin Hu, Zaiwei Zhang et al.

Human drivers rely on commonsense reasoning to navigate diverse and dynamic real-world scenarios. Existing end-to-end (E2E) autonomous driving (AD) models are typically optimized to mimic driving patterns observed in data, without capturing the underlying reasoning processes. This limitation constrains their ability to handle challenging driving scenarios. To close this gap, we propose VLM-AD, a method that leverages vision-language models (VLMs) as teachers to enhance training by providing additional supervision that incorporates unstructured reasoning information and structured action labels. Such supervision enhances the model's ability to learn richer feature representations that capture the rationale behind driving patterns. Importantly, our method does not require a VLM during inference, making it practical for real-time deployment. When integrated with state-of-the-art methods, VLM-AD achieves significant improvements in planning accuracy and reduced collision rates on the nuScenes dataset. It further improves route completion and driving scores under closed-loop evaluation, demonstrating its effectiveness in long-horizon, interactive driving scenarios and its potential for safe and reliable real-world deployment.

Wenbo Shang, Xin Huang

A graph is a fundamental data model to represent various entities and their complex relationships in society and nature, such as social networks, transportation networks, and financial networks. Recently, large language models (LLMs) have showcased a strong generalization ability to handle various natural language processing tasks to answer users' arbitrary questions and generate specific-domain content. Compared with graph learning models, LLMs enjoy superior advantages in addressing the challenges of generalizing graph tasks by eliminating the need for training graph learning models and reducing the cost of manual annotation. However, LLMs are sequential models for textual data, but graphs are non-sequential topological data. It is challenging to adapt LLMs to tackle graph analytics tasks. In this survey, we conduct a comprehensive investigation of existing LLM studies on graph data, which summarizes the relevant graph analytics tasks solved by advanced LLM models and points out the existing challenges and future directions. Specifically, we study the key problems of LLM-based generative graph analytics (LLM-GGA) in terms of three categories: LLM-based graph query processing (LLM-GQP), LLM-based graph inference and learning (LLM-GIL), and graph-LLM-based applications. LLM-GQP focuses on an integration of graph analytics techniques and LLM prompts, including graph understanding and knowledge graphs and LLMs, while LLM-GIL focuses on learning and reasoning over graphs, including graph learning, graph-formed reasoning, and graph representation. We summarize the useful prompts incorporated into LLM to handle different graph downstream tasks. Moreover, we give a summary of LLM model evaluation, benchmark datasets/tasks, and a deep pro and cons analysis of the discussed LLM-GGA models. We also explore open problems and future directions in the research area of LLMs and graph analytics.

Xin Huang, Chul-Ho Lee

Graph neural networks (GNNs) are powerful tools for solving graph-related problems. Distributed GNN frameworks and systems enhance the scalability of GNNs and accelerate model training, yet most are optimized for node classification. Their performance on link prediction remains underexplored. This paper demystifies distributed training of GNNs for link prediction by investigating the issue of performance degradation when each worker trains a GNN on its assigned partitioned subgraph without having access to the entire graph. We discover that the main sources of the issue come from not only the information loss caused by graph partitioning but also the ways of drawing negative samples during model training. While sharing the complete graph information with each worker resolves the issue and preserves link prediction accuracy, it incurs a high communication cost. We propose SpLPG, which effectively leverages graph sparsification to mitigate the issue of performance degradation at a reduced communication cost. Experiment results on several public real-world datasets demonstrate the effectiveness of SpLPG, which reduces the communication overhead by up to about 80% while mostly preserving link prediction accuracy.

Yuyang Deng, Ni Zhao, Xin Huang

Since its launch, ChatGPT has achieved remarkable success as a versatile conversational AI platform, drawing millions of users worldwide and garnering widespread recognition across academic, industrial, and general communities. This paper aims to point a portrait of early GPT users and understand how they evolved. Specific questions include their topics of interest and their potential careers; and how this changes over time. We conduct a detailed analysis of real-world ChatGPT datasets with multi-turn conversations between users and ChatGPT. Through a multi-pronged approach, we quantify conversation dynamics by examining the number of turns, then gauge sentiment to understand user sentiment variations, and finally employ Latent Dirichlet Allocation (LDA) to discern overarching topics within the conversation. By understanding shifts in user demographics and interests, we aim to shed light on the changing nature of human-AI interaction and anticipate future trends in user engagement with language models.

Kaiyuan Wang, Daniel Rall, Greg Tener et al.

Google has a monolithic codebase with tens of millions build targets. Each build target specifies the information that is needed to build a software artifact or run tests. It is common to execute a subset of build targets at each revision and make sure that the change does not break the codebase. Google's build service system uses Bazel to build targets. Bazel takes as input a build that specifies the execution context, flags and build targets to run. The outputs are the build libraries, binaries or test results. To be able to support developer's daily activities, the build service system runs millions of builds per day. It is a known issue that a build with many targets could run out of the allocated memory or exceed its execution deadline. This is problematic because it reduces the developer's productivity, e.g. code submissions or binary releases. In this paper, we propose a technique that predicts the memory usage and executor occupancy of a build. The technique batches a set of targets such that the build created with those targets does not run out of memory or exceed its deadline. This approach significantly reduces the number of builds that run out of memory or exceed the deadlines, hence improving developer's productivity.

Dalong Zhang, Xianzheng Song, Ziqi Liu et al.

Link prediction is widely used in a variety of industrial applications, such as merchant recommendation, fraudulent transaction detection, and so on. However, it's a great challenge to train and deploy a link prediction model on industrial-scale graphs with billions of nodes and edges. In this work, we present a scalable and distributed framework for semi-supervised link prediction problem (named DSSLP), which is able to handle industrial-scale graphs. Instead of training model on the whole graph, DSSLP is proposed to train on the \emph{$k$-hops neighborhood} of nodes in a mini-batch setting, which helps reduce the scale of the input graph and distribute the training procedure. In order to generate negative examples effectively, DSSLP contains a distributed batched runtime sampling module. It implements uniform and dynamic sampling approaches, and is able to adaptively construct positive and negative examples to guide the training process. Moreover, DSSLP proposes a model-split strategy to accelerate the speed of inference process of the link prediction task. Experimental results demonstrate that the effectiveness and efficiency of DSSLP in serval public datasets as well as real-world datasets of industrial-scale graphs.

Soroush Ebadian, Xin Huang

In public-private graphs, users share one public graph and have their own private graphs. A private graph consists of personal private contacts that only can be visible to its owner, e.g., hidden friend lists on Facebook and secret following on Sina Weibo. However, existing public-private analytic algorithms have not yet investigated the dense subgraph discovery of k-truss, where each edge is contained in at least k-2 triangles. This paper aims at finding k-truss efficiently in public-private graphs. The core of our solution is a novel algorithm to update k-truss with node insertions. We develop a classification-based hybrid strategy of node insertions and edge insertions to incrementally compute k-truss in public-private graphs. Extensive experiments validate the superiority of our proposed algorithms against state-of-the-art methods on real-world datasets.

Hanjun Dai, Hui Li, Tian Tian et al.

Deep learning on graph structures has shown exciting results in various applications. However, few attentions have been paid to the robustness of such models, in contrast to numerous research work for image or text adversarial attack and defense. In this paper, we focus on the adversarial attacks that fool the model by modifying the combinatorial structure of data. We first propose a reinforcement learning based attack method that learns the generalizable attack policy, while only requiring prediction labels from the target classifier. Also, variants of genetic algorithms and gradient methods are presented in the scenario where prediction confidence or gradients are available. We use both synthetic and real-world data to show that, a family of Graph Neural Network models are vulnerable to these attacks, in both graph-level and node-level classification tasks. We also show such attacks can be used to diagnose the learned classifiers.