Liang Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Liang Zhang has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Cheng Long
Nanyang technological university, Singapore, Singapore
5 shared publications - Guannan Liu
Beihang University
3 shared publications - Junjie Wu
Beihang University
3 shared publications - Xiaoyang Wang
University of New South Wales
2 shared publications - Aoqi Zuo
The University of Sydney, Sydney, Australia
1 shared publication Cheng Long
1 shared publication
Latest Publications
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 1216-1227
Observationally Informed Adaptive Causal Experimental Design
Randomized Controlled Trials (RCTs) represent the gold standard for causal inference yet remain a scarce resource. While large-scale observational data is often available, it is typically used only for retrospective fusion, and remains discarded in prospective trial design due to bias concerns. We argue that this ''tabula rasa'' data acquisition strategy is inefficient when observational models contain useful structural information. In this work, we propose Active Residual Learning, a new paradigm that leverages the observational model as an informative but biased prior. This shifts the experimental focus from learning target causal quantities from scratch to estimating residual corrections that debias the observational model. To operationalize this, we introduce the R-Design framework. Theoretically, we characterize two key advantages: (1) a conditional structural efficiency gap, showing that estimating lower-complexity residual contrasts can admit faster convergence rates than reconstructing full outcomes; and (2) information efficiency, where we quantify the redundancy in standard parameter-based acquisition, demonstrating that such baselines can waste budget on task-irrelevant nuisance uncertainty. We propose R-EPIG (Residual Expected Predictive Information Gain), a unified criterion that directly targets the downstream causal quantity, reducing residual uncertainty for estimation or clarifying decision boundaries for policy. Experiments on synthetic and semi-synthetic benchmarks show that R-Design significantly outperforms baselines in the intended informative-but-biased regime, supporting the effectiveness of correcting a biased model rather than learning from scratch.
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 1216-1227
Open AccessObservationally Informed Adaptive Causal Experimental Design
Randomized Controlled Trials (RCTs) represent the gold standard for causal inference yet remain a scarce resource. While large-scale observational data is often available, it is typically used only for retrospective fusion, and remains discarded in prospective trial design due to bias concerns. We argue that this ''tabula rasa'' data acquisition strategy is inefficient when observational models contain useful structural information. In this work, we propose Active Residual Learning, a new paradigm that leverages the observational model as an informative but biased prior. This shifts the experimental focus from learning target causal quantities from scratch to estimating residual corrections that debias the observational model. To operationalize this, we introduce the R-Design framework. Theoretically, we characterize two key advantages: (1) a conditional structural efficiency gap, showing that estimating lower-complexity residual contrasts can admit faster convergence rates than reconstructing full outcomes; and (2) information efficiency, where we quantify the redundancy in standard parameter-based acquisition, demonstrating that such baselines can waste budget on task-irrelevant nuisance uncertainty. We propose R-EPIG (Residual Expected Predictive Information Gain), a unified criterion that directly targets the downstream causal quantity, reducing residual uncertainty for estimation or clarifying decision boundaries for policy. Experiments on synthetic and semi-synthetic benchmarks show that R-Design significantly outperforms baselines in the intended informative-but-biased regime, supporting the effectiveness of correcting a biased model rather than learning from scratch.
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 2545-2556
Beyond One-Size-Fits-All: Adaptive Subgraph Denoising for Zero-Shot Graph Learning with Large Language Models
Graph-based tasks in the zero-shot setting remain a significant challenge due to data scarcity and the inability of traditional Graph Neural Networks (GNNs) to generalize to unseen domains or label spaces. While recent advancements have transitioned toward leveraging Large Language Models (LLMs) as predictors to enhance GNNs, these methods often suffer from cross-modal alignment issues. A recent paradigm ( i.e., Graph-R1) overcomes the aforementioned architectural dependencies by adopting a purely text-based format and utilizing LLM-based graph reasoning, showing improved zero-shot generalization. However, it employs a task-agnostic, one-size-fits-all subgraph extraction strategy, which inevitably introduces significant structural noise—irrelevant neighbors and edges—that distorts the LLMs' receptive field and leads to suboptimal predictions. To address this limitation, we introduce GraphSSR, a novel framework designed for adaptive subgraph extraction and denoising in zero-shot LLM-based graph reasoning. Specifically, we propose the SSR pipeline, which dynamically tailors subgraph extraction to specific contexts through a ''Sample-Select-Reason'' process, enabling the model to autonomously filter out task-irrelevant neighbors and overcome the one-size-fits-all issue. To internalize this capability, we develop SSR-SFT, a data synthesis strategy that generates high-quality SSR-style graph reasoning traces for supervised fine-tuning of LLMs. Furthermore, we propose SSR-RL, a two-stage reinforcement learning framework that explicitly regulates sampling and selection operations within the proposed SSR pipeline designed for adaptive subgraph denoising. By incorporating Authenticity-Reinforced and Denoising-Reinforced RL, we guide the model to achieve accurate predictions using parsimonious, denoised subgraphs for reasoning. Extensive experiments across multiple benchmarks demonstrate that GraphSSR significantly outperforms state-of-the-art methods, highlighting the necessity of adaptive subgraph denoising for zero-shot graph reasoning. Our code is publicly available at https://github.com/mysteriouslfz/GraphSSR.
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 2545-2556
Open AccessBeyond One-Size-Fits-All: Adaptive Subgraph Denoising for Zero-Shot Graph Learning with Large Language Models
Graph-based tasks in the zero-shot setting remain a significant challenge due to data scarcity and the inability of traditional Graph Neural Networks (GNNs) to generalize to unseen domains or label spaces. While recent advancements have transitioned toward leveraging Large Language Models (LLMs) as predictors to enhance GNNs, these methods often suffer from cross-modal alignment issues. A recent paradigm ( i.e., Graph-R1) overcomes the aforementioned architectural dependencies by adopting a purely text-based format and utilizing LLM-based graph reasoning, showing improved zero-shot generalization. However, it employs a task-agnostic, one-size-fits-all subgraph extraction strategy, which inevitably introduces significant structural noise—irrelevant neighbors and edges—that distorts the LLMs' receptive field and leads to suboptimal predictions. To address this limitation, we introduce GraphSSR, a novel framework designed for adaptive subgraph extraction and denoising in zero-shot LLM-based graph reasoning. Specifically, we propose the SSR pipeline, which dynamically tailors subgraph extraction to specific contexts through a ''Sample-Select-Reason'' process, enabling the model to autonomously filter out task-irrelevant neighbors and overcome the one-size-fits-all issue. To internalize this capability, we develop SSR-SFT, a data synthesis strategy that generates high-quality SSR-style graph reasoning traces for supervised fine-tuning of LLMs. Furthermore, we propose SSR-RL, a two-stage reinforcement learning framework that explicitly regulates sampling and selection operations within the proposed SSR pipeline designed for adaptive subgraph denoising. By incorporating Authenticity-Reinforced and Denoising-Reinforced RL, we guide the model to achieve accurate predictions using parsimonious, denoised subgraphs for reasoning. Extensive experiments across multiple benchmarks demonstrate that GraphSSR significantly outperforms state-of-the-art methods, highlighting the necessity of adaptive subgraph denoising for zero-shot graph reasoning. Our code is publicly available at https://github.com/mysteriouslfz/GraphSSR.
- Open Access
- 10 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 318-326
HHGT: Hierarchical Heterogeneous Graph Transformer for Heterogeneous Graph Representation Learning
- 10 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 318-326
Open AccessHHGT: Hierarchical Heterogeneous Graph Transformer for Heterogeneous Graph Representation Learning
- Open Access
HHGT: Hierarchical Heterogeneous Graph Transformer for Heterogeneous Graph Representation Learning
Despite the success of Heterogeneous Graph Neural Networks (HGNNs) in modeling real-world Heterogeneous Information Networks (HINs), challenges such as expressiveness limitations and over-smoothing have prompted researchers to explore Graph Transformers (GTs) for enhanced HIN representation learning. However, research on GT in HINs remains limited, with two key shortcomings in existing work: (1) A node's neighbors at different distances in HINs convey diverse semantics. Unfortunately, existing methods ignore such differences and uniformly treat neighbors within a given distance in a coarse manner, which results in semantic confusion. (2) Nodes in HINs have various types, each with unique semantics. Nevertheless, existing methods mix nodes of different types during neighbor aggregation, hindering the capture of proper correlations between nodes of diverse types. To bridge these gaps, we design an innovative structure named (k,t)-ring neighborhood, where nodes are initially organized by their distance, forming different non-overlapping k-ring neighborhoods for each distance. Within each k-ring structure, nodes are further categorized into different groups according to their types, thus emphasizing the heterogeneity of both distances and types in HINs naturally. Based on this structure, we propose a novel Hierarchical Heterogeneous Graph Transformer (HHGT) model, which seamlessly integrates a Type-level Transformer for aggregating nodes of different types within each k-ring neighborhood, followed by a Ring-level Transformer for aggregating different k-ring neighborhoods in a hierarchical manner. Extensive experiments are conducted on downstream tasks to verify HHGT's superiority over 14 baselines, with a notable improvement of up to 24.75% in NMI and 29.25% in ARI for node clustering task on the ACM dataset compared to the best baseline.
Open AccessHHGT: Hierarchical Heterogeneous Graph Transformer for Heterogeneous Graph Representation Learning
Despite the success of Heterogeneous Graph Neural Networks (HGNNs) in modeling real-world Heterogeneous Information Networks (HINs), challenges such as expressiveness limitations and over-smoothing have prompted researchers to explore Graph Transformers (GTs) for enhanced HIN representation learning. However, research on GT in HINs remains limited, with two key shortcomings in existing work: (1) A node's neighbors at different distances in HINs convey diverse semantics. Unfortunately, existing methods ignore such differences and uniformly treat neighbors within a given distance in a coarse manner, which results in semantic confusion. (2) Nodes in HINs have various types, each with unique semantics. Nevertheless, existing methods mix nodes of different types during neighbor aggregation, hindering the capture of proper correlations between nodes of diverse types. To bridge these gaps, we design an innovative structure named (k,t)-ring neighborhood, where nodes are initially organized by their distance, forming different non-overlapping k-ring neighborhoods for each distance. Within each k-ring structure, nodes are further categorized into different groups according to their types, thus emphasizing the heterogeneity of both distances and types in HINs naturally. Based on this structure, we propose a novel Hierarchical Heterogeneous Graph Transformer (HHGT) model, which seamlessly integrates a Type-level Transformer for aggregating nodes of different types within each k-ring neighborhood, followed by a Ring-level Transformer for aggregating different k-ring neighborhoods in a hierarchical manner. Extensive experiments are conducted on downstream tasks to verify HHGT's superiority over 14 baselines, with a notable improvement of up to 24.75% in NMI and 29.25% in ARI for node clustering task on the ACM dataset compared to the best baseline.
- 2 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 36 (7) , 2942-2955
Denoising Item Graph With Disentangled Learning for Recommendation
Recent years have witnessed the growth of Graph-based Collaborative Filtering (GCF) for high-performance recommendations, but the widely adopted user-item bipartite graphs are subject to deeper layers’ over-smoothing effect and sparse user-item interactions when learning item representations. In this work, we introduce item graph , which regards items as nodes and connecting those that have ever co-occurred in transactions with edges, to preserve higher-order item relations while avoiding the drawbacks of bipartite graphs for item-based recommendation. To cope with the entangled semantics in the edges of an item graph, we first design a denoising scheme via a graph structure learning module with discrete sampling to drop noisy edges with respect to certain latent aspects, where multiple subgraphs can be yielded. We then implement graphical disentangled learning by imposing several structural regularizers that allow for macro conformity and micro divergence among the subgraphs. Finally, we propose a multi-graph fusion module to aggregate users’ preferences in different subgraphs with a user-graph attention mechanism. Extensive experiments on 5 real-world datasets demonstrate the superiority of our method over 16 competitive baseline methods including the recently proposed GCF ones. Particularly, our method shows evident advantages in recommendation under data sparsity conditions.
- 2 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 36 (7) , 2942-2955
Denoising Item Graph With Disentangled Learning for Recommendation
Recent years have witnessed the growth of Graph-based Collaborative Filtering (GCF) for high-performance recommendations, but the widely adopted user-item bipartite graphs are subject to deeper layers’ over-smoothing effect and sparse user-item interactions when learning item representations. In this work, we introduce item graph , which regards items as nodes and connecting those that have ever co-occurred in transactions with edges, to preserve higher-order item relations while avoiding the drawbacks of bipartite graphs for item-based recommendation. To cope with the entangled semantics in the edges of an item graph, we first design a denoising scheme via a graph structure learning module with discrete sampling to drop noisy edges with respect to certain latent aspects, where multiple subgraphs can be yielded. We then implement graphical disentangled learning by imposing several structural regularizers that allow for macro conformity and micro divergence among the subgraphs. Finally, we propose a multi-graph fusion module to aggregate users’ preferences in different subgraphs with a user-graph attention mechanism. Extensive experiments on 5 real-world datasets demonstrate the superiority of our method over 16 competitive baseline methods including the recently proposed GCF ones. Particularly, our method shows evident advantages in recommendation under data sparsity conditions.
- Open Access
- 18 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 1303-1312
Next Basket Recommendation with Intent-aware Hypergraph Adversarial Network
Next Basket Recommendation (NBR) that recommends a basket of items to users has become a promising promotion artifice for online businesses. The key challenge of NBR is rooted in the complicated relations of items that are dependent on one another in a same basket with users' diverse purchasing intentions, which goes far beyond the pairwise item relations in traditional recommendation tasks, and yet has not been well addressed by existing NBR methods that mostly model the inter-basket item relations only. To that end, in this paper, we construct a hypergraph from basket-wise purchasing records and probe the inter-basket and intra-basket item relations behind the hyperedges. In particular, we combine the strength of HyperGraph Neural Network with disentangled representation learning to derive the intent-aware representations of hyperedges for characterizing the nuances of user purchasing patterns. Moreover, considering the information loss in traditional item-wise optimization, we propose a novel basket-wise optimization scheme via an adversarial network to generate high-quality negative baskets. Extensive experiments conducted on four different data sets demonstrate the superior performances over the state-of-the-art NBR methods. Notably, our method is shown to strike a good balance in recommending both repeated and explorative items as a basket.
- 18 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 1303-1312
Open AccessNext Basket Recommendation with Intent-aware Hypergraph Adversarial Network
Next Basket Recommendation (NBR) that recommends a basket of items to users has become a promising promotion artifice for online businesses. The key challenge of NBR is rooted in the complicated relations of items that are dependent on one another in a same basket with users' diverse purchasing intentions, which goes far beyond the pairwise item relations in traditional recommendation tasks, and yet has not been well addressed by existing NBR methods that mostly model the inter-basket item relations only. To that end, in this paper, we construct a hypergraph from basket-wise purchasing records and probe the inter-basket and intra-basket item relations behind the hyperedges. In particular, we combine the strength of HyperGraph Neural Network with disentangled representation learning to derive the intent-aware representations of hyperedges for characterizing the nuances of user purchasing patterns. Moreover, considering the information loss in traditional item-wise optimization, we propose a novel basket-wise optimization scheme via an adversarial network to generate high-quality negative baskets. Extensive experiments conducted on four different data sets demonstrate the superior performances over the state-of-the-art NBR methods. Notably, our method is shown to strike a good balance in recommending both repeated and explorative items as a basket.
- Open Access
- 15 June 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 17 (9) , 1-25
Road Network Representation Learning: A Dual Graph-based Approach
Road network is a critical infrastructure powering many applications including transportation, mobility and logistics in real life. To leverage the input of a road network across these different applications, it is necessary to learn the representations of the roads in the form of vectors, which is namedroad network representation learning(RNRL). While several models have been proposed for RNRL, they capture the pairwise relationships/connections among roads only (i.e., as a simple graph), and fail to capture among roads the high-order relationships (e.g., those roads that jointly form a local region usually have similar features such as speed limit) and long-range relationships (e.g., some roads that are far apart may have similar semantics such as being roads in residential areas). Motivated by this, we propose to construct ahypergraph, where each hyperedge corresponds to a set of multiple roads forming a region. The constructed hypergraph would naturally capture the high-order relationships among roads with hyperedges. We then allow information propagation via both the edges in the simple graph and the hyperedges in the hypergraph in a graph neural network context. In addition, we introduce different pretext tasks based on both the simple graph (i.e., graph reconstruction) and the hypergraph (including hypergraph reconstruction and hyperedge classification) for optimizing the representations of roads. The graph reconstruction and hypergraph reconstruction tasks are conventional ones and can capture structural information. The hyperedge classification task can capture long-range relationships between pairs of roads that belong to hyperedges with the same label. We call the resulting modelHyperRoad. We further extend HyperRoad to problem settings when additional inputs of road attributes and/or trajectories that are generated on the roads are available. We conduct extensive experiments on two real datasets, for five downstream tasks, and under four problem settings, which demonstrate that our model achieves impressive improvements compared with existing baselines across datasets, tasks, problem settings, and performance metrics.CCS Concepts: • Information systems→Data mining; • Urban computing; • Spatial-temporal systems;
- 15 June 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 17 (9) , 1-25
Open AccessRoad Network Representation Learning: A Dual Graph-based Approach
Road network is a critical infrastructure powering many applications including transportation, mobility and logistics in real life. To leverage the input of a road network across these different applications, it is necessary to learn the representations of the roads in the form of vectors, which is namedroad network representation learning(RNRL). While several models have been proposed for RNRL, they capture the pairwise relationships/connections among roads only (i.e., as a simple graph), and fail to capture among roads the high-order relationships (e.g., those roads that jointly form a local region usually have similar features such as speed limit) and long-range relationships (e.g., some roads that are far apart may have similar semantics such as being roads in residential areas). Motivated by this, we propose to construct ahypergraph, where each hyperedge corresponds to a set of multiple roads forming a region. The constructed hypergraph would naturally capture the high-order relationships among roads with hyperedges. We then allow information propagation via both the edges in the simple graph and the hyperedges in the hypergraph in a graph neural network context. In addition, we introduce different pretext tasks based on both the simple graph (i.e., graph reconstruction) and the hypergraph (including hypergraph reconstruction and hyperedge classification) for optimizing the representations of roads. The graph reconstruction and hypergraph reconstruction tasks are conventional ones and can capture structural information. The hyperedge classification task can capture long-range relationships between pairs of roads that belong to hyperedges with the same label. We call the resulting modelHyperRoad. We further extend HyperRoad to problem settings when additional inputs of road attributes and/or trajectories that are generated on the roads are available. We conduct extensive experiments on two real datasets, for five downstream tasks, and under four problem settings, which demonstrate that our model achieves impressive improvements compared with existing baselines across datasets, tasks, problem settings, and performance metrics.CCS Concepts: • Information systems→Data mining; • Urban computing; • Spatial-temporal systems;
- Open Access
Road Network Representation Learning: A Dual Graph based Approach
Road network is a critical infrastructure powering many applications including transportation, mobility and logistics in real life. To leverage the input of a road network across these different applications, it is necessary to learn the representations of the roads in the form of vectors, which is named \emph{road network representation learning} (RNRL). While several models have been proposed for RNRL, they capture the pairwise relationships/connections among roads only (i.e., as a simple graph), and fail to capture among roads the high-order relationships (e.g., those roads that jointly form a local region usually have similar features such as speed limit) and long-range relationships (e.g., some roads that are far apart may have similar semantics such as being roads in residential areas). Motivated by this, we propose to construct a \emph{hypergraph}, where each hyperedge corresponds to a set of multiple roads forming a region. The constructed hypergraph would naturally capture the high-order relationships among roads with hyperedges. We then allow information propagation via both the edges in the simple graph and the hyperedges in the hypergraph in a graph neural network context. The graph reconstruction and hypergraph reconstruction tasks are conventional ones and can capture structural information. The hyperedge classification task can capture long-range relationships between pairs of roads that belong to hyperedges with the same label. We call the resulting model \emph{HyperRoad}. We further extend HyperRoad to problem settings when additional inputs of road attributes and/or trajectories that are generated on the roads are available.
Open AccessRoad Network Representation Learning: A Dual Graph based Approach
Road network is a critical infrastructure powering many applications including transportation, mobility and logistics in real life. To leverage the input of a road network across these different applications, it is necessary to learn the representations of the roads in the form of vectors, which is named \emph{road network representation learning} (RNRL). While several models have been proposed for RNRL, they capture the pairwise relationships/connections among roads only (i.e., as a simple graph), and fail to capture among roads the high-order relationships (e.g., those roads that jointly form a local region usually have similar features such as speed limit) and long-range relationships (e.g., some roads that are far apart may have similar semantics such as being roads in residential areas). Motivated by this, we propose to construct a \emph{hypergraph}, where each hyperedge corresponds to a set of multiple roads forming a region. The constructed hypergraph would naturally capture the high-order relationships among roads with hyperedges. We then allow information propagation via both the edges in the simple graph and the hyperedges in the hypergraph in a graph neural network context. The graph reconstruction and hypergraph reconstruction tasks are conventional ones and can capture structural information. The hyperedge classification task can capture long-range relationships between pairs of roads that belong to hyperedges with the same label. We call the resulting model \emph{HyperRoad}. We further extend HyperRoad to problem settings when additional inputs of road attributes and/or trajectories that are generated on the roads are available.
- 7 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 35 (9) , 9031-9036
Region Embedding With Intra and Inter-View Contrastive Learning
Unsupervised region representation learning aims to extract dense and effective features from unlabeled urban data. While some efforts have been made for solving this problem based on multiple views, existing methods are still insufficient in extracting representations in a view and/or incorporating representations from different views. Motivated by the success of contrastive learning for representation learning, we propose to leverage it for multi-view region representation learning and design a model called ReMVC (Region Embedding with Multi-View Contrastive Learning) by following two guidelines:$i$ ) comparing a region with others within each view for effective representation extraction and$ii$ ) comparing a region with itself across different views for cross-view information sharing. We design the intra-view contrastive learning module which helps to learn distinguished region embeddings and the inter-view contrastive learning module which serves as a soft co-regularizer to constrain the embedding parameters and transfer knowledge across multi-views. We exploit the learned region embeddings in two downstream tasks named land usage clustering and region popularity prediction. Extensive experiments demonstrate that our model achieves impressive improvements compared with seven state-of-the-art baseline methods, and the margins are over 30% in the land usage clustering task.- 7 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 35 (9) , 9031-9036
Region Embedding With Intra and Inter-View Contrastive Learning
Unsupervised region representation learning aims to extract dense and effective features from unlabeled urban data. While some efforts have been made for solving this problem based on multiple views, existing methods are still insufficient in extracting representations in a view and/or incorporating representations from different views. Motivated by the success of contrastive learning for representation learning, we propose to leverage it for multi-view region representation learning and design a model called ReMVC (Region Embedding with Multi-View Contrastive Learning) by following two guidelines:$i$ ) comparing a region with others within each view for effective representation extraction and$ii$ ) comparing a region with itself across different views for cross-view information sharing. We design the intra-view contrastive learning module which helps to learn distinguished region embeddings and the inter-view contrastive learning module which serves as a soft co-regularizer to constrain the embedding parameters and transfer knowledge across multi-views. We exploit the learned region embeddings in two downstream tasks named land usage clustering and region popularity prediction. Extensive experiments demonstrate that our model achieves impressive improvements compared with seven state-of-the-art baseline methods, and the margins are over 30% in the land usage clustering task.- Open Access
Region Embedding with Intra and Inter-View Contrastive Learning
Unsupervised region representation learning aims to extract dense and effective features from unlabeled urban data. While some efforts have been made for solving this problem based on multiple views, existing methods are still insufficient in extracting representations in a view and/or incorporating representations from different views. Motivated by the success of contrastive learning for representation learning, we propose to leverage it for multi-view region representation learning and design a model called ReMVC (Region Embedding with Multi-View Contrastive Learning) by following two guidelines: i) comparing a region with others within each view for effective representation extraction and ii) comparing a region with itself across different views for cross-view information sharing. We design the intra-view contrastive learning module which helps to learn distinguished region embeddings and the inter-view contrastive learning module which serves as a soft co-regularizer to constrain the embedding parameters and transfer knowledge across multi-views. We exploit the learned region embeddings in two downstream tasks named land usage clustering and region popularity prediction. Extensive experiments demonstrate that our model achieves impressive improvements compared with seven state-of-the-art baseline methods, and the margins are over 30% in the land usage clustering task.
Open AccessRegion Embedding with Intra and Inter-View Contrastive Learning
Unsupervised region representation learning aims to extract dense and effective features from unlabeled urban data. While some efforts have been made for solving this problem based on multiple views, existing methods are still insufficient in extracting representations in a view and/or incorporating representations from different views. Motivated by the success of contrastive learning for representation learning, we propose to leverage it for multi-view region representation learning and design a model called ReMVC (Region Embedding with Multi-View Contrastive Learning) by following two guidelines: i) comparing a region with others within each view for effective representation extraction and ii) comparing a region with itself across different views for cross-view information sharing. We design the intra-view contrastive learning module which helps to learn distinguished region embeddings and the inter-view contrastive learning module which serves as a soft co-regularizer to constrain the embedding parameters and transfer knowledge across multi-views. We exploit the learned region embeddings in two downstream tasks named land usage clustering and region popularity prediction. Extensive experiments demonstrate that our model achieves impressive improvements compared with seven state-of-the-art baseline methods, and the margins are over 30% in the land usage clustering task.