One fundamental challenge in graph machine learning is generalizing to new graphs. Many existing methods following the inductive setup can generalize to test graphs with new structures, but assuming the feature and label spaces remain the same as the training ones. This paper introduces a fully-inductive setup, where models should perform inference on arbitrary test graphs with new structures, feature and label spaces. We propose GraphAny as the first attempt at this challenging setup. GraphAny models inference on a new graph as an analytical solution to a LinearGNN, which can be naturally applied to graphs with any feature and label spaces. To further build a stronger model with learning capacity, we fuse multiple LinearGNN predictions with learned inductive attention scores. Specifically, the attention module is carefully parameterized as a function of the entropy-normalized distance features between pairs of LinearGNN predictions to ensure generalization to new graphs. Empirically, GraphAny trained on a single Wisconsin dataset with only 120 labeled nodes can generalize to 30 new graphs with an average accuracy of 67.26%, surpassing not only all inductive baselines, but also strong transductive methods trained separately on each of the 30 test graphs.

Efficient long-context modeling remains a critical challenge for natural language processing (NLP), as the time complexity of the predominant Transformer architecture scales quadratically with the sequence length. While state-space models (SSMs) offer alternative sub-quadratic solutions, they struggle to capture long-range dependencies effectively. In this work, we focus on analyzing and improving the long-context modeling capabilities of SSMs. We show that the widely used synthetic task, associative recall, which requires a model to recall a value associated with a single key without context, insufficiently represents the complexities of real-world long-context modeling. To address this limitation, we extend the associative recall to a novel synthetic task, joint recall, which requires a model to recall the value associated with a key given in a specified context. Theoretically, we prove that SSMs do not have the expressiveness to solve multi-query joint recall in sub-quadratic time complexity. To resolve this issue, we propose a solution based on integrating SSMs with Context-Dependent Sparse Attention (CDSA), which has the expressiveness to solve multi-query joint recall with sub-quadratic computation. To bridge the gap between theoretical analysis and real-world applications, we propose locality-sensitive Hashing Attention with sparse Key Selection (HAX), which instantiates the theoretical solution and is further tailored to natural language domains. Extensive experiments on both synthetic and real-world long-context benchmarks show that HAX consistently outperforms SSM baselines and SSMs integrated with context-independent sparse attention (CISA). Our code is available at: https://github.com/DeepGraphLearning/HAX.

Le Zhuo, Zewen Chi, Minghao Xu, Heyan Huang, Jianan Zhao, Heqi Zheng, Conghui He, Xian-Ling Mao, Wentao Zhang. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Graph Foundation Models (GFMs) are emerging as a significant research topic in the graph domain, aiming to develop graph models trained on extensive and diverse data to enhance their applicability across various tasks and domains. Developing GFMs presents unique challenges over traditional Graph Neural Networks (GNNs), which are typically trained from scratch for specific tasks on particular datasets. The primary challenge in constructing GFMs lies in effectively leveraging vast and diverse graph data to achieve positive transfer. Drawing inspiration from existing foundation models in the CV and NLP domains, we propose a novel perspective for the GFM development by advocating for a "graph vocabulary'', in which the basic transferable units underlying graphs encode the invariance on graphs. We ground the graph vocabulary construction from essential aspects including network analysis, expressiveness, and stability. Such a vocabulary perspective can potentially advance the future GFM design in line with the neural scaling laws. All relevant resources with GFM design can be found here.

Transcriptome foundation models (TFMs) hold great promises of deciphering the transcriptomic language that dictate diverse cell functions by self-supervised learning on large-scale single-cell gene expression data, and ultimately unraveling the complex mechanisms of human diseases. However, current TFMs treat cells as independent samples and ignore the taxonomic relationships between cell types, which are available in cell ontology graphs. We argue that effectively leveraging this ontology information during the TFM pre-training can improve learning biologically meaningful gene co-expression patterns while preserving TFM as a general purpose foundation model for downstream zero-shot and fine-tuning tasks. To this end, we present **s**ingle **c**ell, **Cell**-**o**ntology guided TFM (scCello). We introduce cell-type coherence loss and ontology alignment loss, which are minimized along with the masked gene expression prediction loss during the pre-training. The novel loss component guide scCello to learn the cell-type-specific representation and the structural relation between cell types from the cell ontology graph, respectively. We pre-trained scCello on 22 million cells from CellxGene database leveraging their cell-type labels mapped to the cell ontology graph from Open Biological and Biomedical Ontology Foundry. Our TFM demonstrates competitive generalization and transferability performance over the existing TFMs on biologically important tasks including identifying novel cell types of unseen cells, prediction of cell-type-specific marker genes, and cancer drug responses. Source code and model weights are available at https://github.com/DeepGraphLearning/scCello.

Rui Li, Xu Chen, Chaozhuo Li, Yanming Shen, Jianan Zhao, Yujing Wang, Weihao Han, Hao Sun, Weiwei Deng, Qi Zhang, Xing Xie. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Text-attributed graphs (TAGs) are prevalent in various real-world scenarios, where each node is associated with a text description. The cornerstone of representation learning on TAGs lies in the seamless integration of textual semantics within individual nodes and the topological connections across nodes. Recent advancements in pre-trained language models (PLMs) and graph neural networks (GNNs) have facilitated effective learning on TAGs, garnering increased research interest. However, the absence of meaningful benchmark datasets and standardized evaluation procedures for TAGs has impeded progress in this field. In this paper, we propose CS-TAG, a comprehensive and diverse collection of challenging benchmark datasets for TAGs. The CS-TAG datasets are notably large in scale and encompass a wide range of domains, spanning from citation networks to purchase graphs. In addition to building the datasets, we conduct extensive benchmark experiments over CS-TAG with various learning paradigms, including PLMs, GNNs, PLM-GNN co-training methods, and the proposed novel topological pre-training of language models. In a nutshell, we provide an overview of the CS-TAG datasets, standardized evaluation procedures, and present baseline experiments. The entire CS-TAG project is publicly accessible at \url{https://github.com/sktsherlock/TAG-Benchmark}.

Graph structure learning (GSL), which aims to learn the adjacency matrix for graph neural networks (GNNs), has shown great potential in boosting the performance of GNNs. Most existing GSL works apply a joint learning framework where the estimated adjacency matrix and GNN parameters are optimized for downstream tasks. However, as GSL is essentially a link prediction task, whose goal may largely differ from the goal of the downstream task. The inconsistency of these two goals limits the GSL methods to learn the potential optimal graph structure. Moreover, the joint learning framework suffers from scalability issues in terms of time and space during the process of estimation and optimization of the adjacency matrix. To mitigate these issues, we propose a graph structure refinement (GSR) framework with a pretrain-finetune pipeline. Specifically, The pre-training phase aims to comprehensively estimate the underlying graph structure by a multi-view contrastive learning framework with both intra- and inter-view link prediction tasks. Then, the graph structure is refined by adding and removing edges according to the edge probabilities estimated by the pre-trained model. Finally, the fine-tuning GNN is initialized by the pre-trained model and optimized toward downstream tasks. With the refined graph structure remaining static in the fine-tuning space, GSR avoids estimating and optimizing graph structure in the fine-tuning phase which enjoys great scalability and efficiency. Moreover, the fine-tuning GNN is boosted by both migrating knowledge and refining graphs. Extensive experiments are conducted to evaluate the effectiveness (best performance on six benchmark datasets), efficiency, and scalability (13.8 times faster using 32.8% GPU memory compared to the best GSL baseline on Cora) of the proposed model.

Graph neural networks (GNNs) have demonstrated great success in representation learning for graph-structured data. The layer-wise graph convolution in GNNs is shown to be powerful at capturing graph topology. During this process, GNNs are usually guided by pre-defined kernels such as Laplacian matrix, adjacency matrix, or their variants. However, the adoptions of pre-defined kernels may restrain the generalities to different graphs: mismatch between graph and kernel would entail sub-optimal performance. For example, GNNs that focus on low-frequency information may not achieve satisfactory performance when high-frequency information is significant for the graphs, and vice versa. To solve this problem, in this paper, we propose a novel framework - i.e., namely Adaptive Kernel Graph Neural Network (AKGNN) - which learns to adapt to the optimal graph kernel in a unified manner at the first attempt. In the proposed AKGNN, we first design a data-driven graph kernel learning mechanism, which adaptively modulates the balance between all-pass and low-pass filters by modifying the maximal eigenvalue of the graph Laplacian. Through this process, AKGNN learns the optimal threshold between high and low frequency signals to relieve the generality problem. Later, we further reduce the number of parameters by a parameterization trick and enhance the expressive power by a global readout function. Extensive experiments are conducted on acknowledged benchmark datasets and promising results demonstrate the outstanding performance of our proposed AKGNN by comparison with state-of-the-art GNNs. The source code is publicly available at: https://github.com/jumxglhf/AKGNN.

The effectiveness of knowledge graph embedding (KGE) largely depends on the ability to model intrinsic relation patterns and mapping properties. However, existing approaches can only capture some of them with insufficient modeling capacity. In this work, we propose a more powerful KGE framework named HousE, which involves a novel parameterization based on two kinds of Householder transformations: (1) Householder rotations to achieve superior capacity of modeling relation patterns; (2) Householder projections to handle sophisticated relation mapping properties. Theoretically, HousE is capable of modeling crucial relation patterns and mapping properties simultaneously. Besides, HousE is a generalization of existing rotation-based models while extending the rotations to high-dimensional spaces. Empirically, HousE achieves new state-of-the-art performance on five benchmark datasets. Our code is available at https://github.com/anrep/HousE.

Prescription (aka Rx) drugs can be easily overprescribed and lead to drug abuse or opioid overdose. Accordingly, a state-run prescription drug monitoring program (PDMP) in the United States has been developed to reduce overprescribing. However, PDMP has limited capability in detecting patients' potential overprescribing behaviors, impairing its effectiveness in preventing drug abuse and overdose in patients. In this paper, we propose a novel model RxNet, which builds 1) a dynamic heterogeneous graph to model Rx refills that are essentially prescribing and dispensing (P&D) relationships among various patients, 2) an RxLSTM network to explore the dynamic Rx-refill behavior and medical condition variation of patients, and 3) a dosing-adaptive network to extract and recalibrate dosing patterns and obtain the refined patient representations which are finally utilized for overprescribing detection. The extensive experimental results on a one-year state-wide PDMP data demonstrate that RxNet consistently outperforms state-of-the-art methods in predicting patients at high risk of opioid overdose and drug abuse.

As the fundamental basis of sponsored search, relevance modeling measures the closeness between the input queries and the candidate ads. Conventional relevance models solely rely on the textual data, which suffer from the scarce semantic signals within the short queries. Recently, user historical click behaviors are incorporated in the format of click graphs to provide additional correlations beyond pure textual semantics, which contributes to advancing the relevance modeling performance. However, user behaviors are usually arbitrary and unpredictable, leading to the noisy and sparse graph topology. In addition, there exist other types of user behaviors besides clicks, which may also provide complementary information. In this paper, we study the novel problem of heterogeneous behavior graph learning to facilitate relevance modeling task. Our motivation lies in learning an optimal and task-relevant heterogeneous behavior graph consisting of multiple types of user behaviors. We further propose a novel HBGLR model to learn the behavior graph structure by mining the sophisticated correlations between node semantics and graph topology, and encode the textual semantics and structural heterogeneity into the learned representations. Our proposal is evaluated over real-world industry datasets, and has been mainstreamed in the Bing ads. Both offline and online experimental results demonstrate its superiority.

Prohibited item detection is an important problem in e-commerce, where the goal is to detect illegal items online for evading risks and stemming crimes. Traditional solutions usually mine evidence from individual instances, while current efforts try employing advanced Graph Neural Networks (GNN) to utilize multiple risk-relevant structures of items. However, it still remains two essential challenges, including weak structure and weak supervision. This work proposes the Risk Graph Structure Learning model (RGSL) for prohibited item detection. RGSL first introduces structure learning into large-scale risk graphs, to reduce noisy connections and add similar pairs. It then designs the pairwise training mechanism, which transforms the detection process as a metric learning from candidates to their similar prohibited items. Furthermore, RGSL generates risk-aware item representations and searches risk-relevant pairs for structure learning iteratively. We test RGSL on three real-world scenarios, and the improvements to baselines are up to 21.91% in AP and 18.28% in MAX-F1. Meanwhile, RGSL has been deployed on an e-commerce platform, and the improvements to traditional solutions are up to 23.59% in [email protected] and 6.52% in [email protected]

Heterogeneous Graph Neural Networks (HGNNs) have drawn increasing attention in recent years and achieved outstanding performance in many tasks. The success of the existing HGNNs relies on one fundamental assumption, i.e., the original heterogeneous graph structure is reliable. However, this assumption is usually unrealistic, since the heterogeneous graph in reality is inevitably noisy or incomplete. Therefore, it is vital to learn the heterogeneous graph structure for HGNNs rather than rely only on the raw graph structure. In light of this, we make the first attempt towards learning an optimal heterogeneous graph structure for HGNNs and propose a novel framework HGSL, which jointly performs Heterogeneous Graph Structure Learning and GNN parameters learning for classification task. Different from traditional GSL on homogeneous graph, considering the heterogeneity of different relations in heterogeneous graph, HGSL generates each relation subgraph independently. Specifically, in each generated relation subgraph, HGSL not only considers the feature similarity by generating feature similarity graph, but also considers the complex heterogeneous interactions in features and semantics by generating feature propagation graph and semantic graph. Then, these graphs are fused to a learned heterogeneous graph and optimized together with a GNN towards classification objective. Extensive experiments on real-world graphs demonstrate that the proposed framework significantly outperforms the state-of-the-art methods.

Prescription (aka Rx) drugs can be easily overprescribed and lead to drug abuse or opioid overdose. Accordingly, a state-run prescription drug monitoring program (PDMP) in the United States has been developed to reduce Overprescribing. However, PDMP has limited capability in detecting patients' potential overprescribing behaviors, impairing its effectiveness in preventing drug abuse and overdose in patients. Despite a few machine-learning-based methods that have been proposed for detecting overprescribing, they usually ignore the patient prescribing behavior and their performances are not satisfying. In light of this, we propose a novel model RxNet for overprescribing detection in PDMP. RxNet builds a dynamic heterogeneous graph to model Rx refills that are essentially prescribing and dispensing (P&D) relationships among various Rx entries (e.g., patients) whose representations are encoded by graph neural network. In addition, to explore the dynamic Rx-refill behavior and medical condition variation of patients, an RxLSTM network is designed to update representations of patients. Based on the output of RxLSTM, a dosing-adaptive network is leveraged to extract and recalibrate dosing patterns and obtain the refined patient representations which are finally utilized for overprescribing detection. The extensive experimental results on a 1-year Ohio PDMP data demonstrate that RxNet consistently outperforms state-of-the-art methods in predicting patients at high risk of opioid overdose and drug abuse, with an average of 5.7% and 7.3% improvement on F1 score respectively.

As heterogeneous networks have become increasingly ubiquitous, Heterogeneous Information Network (HIN) embedding, aiming to project nodes into a low-dimensional space while preserving the heterogeneous structure, has drawn increasing attention in recent years. Many of the existing HIN embedding methods adopt meta-path guided random walk to retain both the semantics and structural correlations between different types of nodes. However, the selection of meta-paths is still an open problem, which either depends on domain knowledge or is learned from label information. As a uniform blueprint of HIN, the network schema comprehensively embraces the high-order structure and contains rich semantics. In this paper, we make the first attempt to study network schema preserving HIN embedding, and propose a novel model named NSHE. In NSHE, a network schema sampling method is first proposed to generate sub-graphs (i.e., schema instances), and then multi-task learning task is built to preserve the heterogeneous structure of each schema instance. Besides preserving pairwise structure information, NSHE is able to retain high-order structure (i.e., network schema). Extensive experiments on three real-world datasets demonstrate that our proposed model NSHE significantly outperforms the state-of-the-art methods.