Lu Lin (林璐)

Selected Publications [full list]

1. ICML

   FusionRetro: Molecule Representation Fusion via In-Context Learning for Retrosynthetic Planning

   Songtao Liu, Zhengkai Tu, Minkai Xu, Zuobai Zhang, Lu Lin, Rex Ying, Jian Tang, Peilin Zhao, and Dinghao Wu

   Proceedings of the 40th International Conference on Machine Learning, ICML 2023

   Abs HTML PDF Code

   Retrosynthetic planning aims to devise a complete multi-step synthetic route from starting materials to a target molecule. Current strategies use a decoupled approach of single-step retrosynthesis models and search algorithms, taking only the product as the input to predict the reactants for each planning step and ignoring valuable context information along the synthetic route. In this work, we propose a novel framework that utilizes context information for improved retrosynthetic planning. We view synthetic routes as reaction graphs and propose to incorporate context through three principled steps: encode molecules into embeddings, aggregate information over routes, and readout to predict reactants. Our approach is the first attempt to utilize in-context learning for retrosynthesis prediction in retrosynthetic planning. The entire framework can be efficiently optimized in an end-to-end fashion and produce more practical and accurate predictions. Comprehensive experiments demonstrate that by fusing in the context information over routes, our model significantly improves the performance of retrosynthetic planning over baselines that are not context-aware, especially for long synthetic routes. Code is available at Github.

2. ICML

   Graph Contrastive Backdoor Attacks

   Hangfan Zhang, Jinghui Chen, Lu Lin, Jinyuan Jia, and Dinghao Wu

   Proceedings of the 40th International Conference on Machine Learning, ICML 2023

   Abs HTML PDF

   Graph Contrastive Learning (GCL) has attracted considerable interest due to its impressive node representation learning capability. Despite the wide application of GCL techniques, little attention has been paid to the security of GCL. In this paper, we systematically study the vulnerability of GCL in the presence of malicious backdoor adversaries. In particular, we propose *GCBA*, the first backdoor attack for graph contrastive learning. GCBA incorporates three attacks: poisoning, crafting, and natural backdoor, each targeting one stage of the GCL pipeline. We formulate our attacks as optimization problems and solve them with a novel discrete optimization technique to overcome the discrete nature of graph-structured data. By extensively evaluating GCBA on multiple datasets and GCL methods, we show that our attack can achieve high attack success rates while preserving stealthiness. We further consider potential countermeasures to our attack and conclude that existing defenses are insufficient to mitigate GCBA. We show that as a complex paradigm involving data and model republishing, GCL is vulnerable to backdoor attacks, and specifically designed defenses are needed to mitigate the backdoor attacks on GCL.

3. ICLR

   Spectral augmentation for self-supervised learning on graphs

   Lu Lin, Jinghui Chen, and Hongning Wang

   Proceedings of the 11th International Conference on Learning Representations, ICLR 2023

   Abs HTML PDF Code

   Graph contrastive learning (GCL), as an emerging self-supervised learning technique on graphs, aims to learn representations via instance discrimination. Its performance heavily relies on graph augmentation to reflect invariant patterns that are robust to small perturbations; yet it still remains unclear about what graph invariance GCL should capture. Recent studies mainly perform topology augmentations in a uniformly random manner in the spatial domain, ignoring its influence on the intrinsic structural properties embedded in the spectral domain. In this work, we aim to find a principled way for topology augmentations by exploring the invariance of graphs from the spectral perspective. We develop spectral augmentation which guides topology augmentations by maximizing the spectral change. Extensive experiments on both graph and node classification tasks demonstrate the effectiveness of our method in self-supervised representation learning. The proposed method also brings promising generalization capability in transfer learning, and is equipped with intriguing robustness property under adversarial attacks. Our study sheds light on a general principle for graph topology augmentation.

4. KDD

   Graph Structural Attack by Perturbing Spectral Distance

   Lu Lin, Ethan Blaser, and Hongning Wang

   Proceedings of the 28th ACM SIGKDD international conference on knowledge discovery & data mining, KDD 2022

   Abs HTML PDF Code

   Graph Convolutional Networks (GCNs) have fueled a surge of interest due to their superior performance on graph learning tasks, but are also shown vulnerability to adversarial attacks. In this paper, an effective graph structural attack is investigated to disrupt graph spectral filters in the Fourier domain. We define the spectral distance based on the eigenvalues of graph Laplacian to measure the disruption of spectral filters. We then generate edge perturbations by simultaneously maximizing a task-specific attack objective and the proposed spectral distance. The experiments demonstrate remarkable effectiveness of the proposed attack in the white-box setting at both training and test time. Our qualitative analysis shows the connection between the attack behavior and the imposed changes on the spectral distribution, which provides empirical evidence that maximizing spectral distance is an effective manner to change the structural property of graphs in the spatial domain and perturb the frequency components in the Fourier domain.

5. ICML

   Communication-Efficient Adaptive Federated Learning

   Yujia Wang, Lu Lin, and Jinghui Chen

   Proceedings of the 39th International Conference on Machine Learning, ICML 2022

   Abs HTML

   Due to the explosion in the size of the training datasets, distributed learning has received growing interest in recent years. One of the major bottlenecks is the large communication cost between the central server and the local workers. While error feedback compression has been proven to be successful in reducing communication costs with stochastic gradient descent (SGD), there are much fewer attempts in building communication-efficient adaptive gradient methods with provable guarantees, which are widely used in training large-scale machine learning models. In this paper, we propose a new communication-compressed AMSGrad for distributed nonconvex optimization problem, which is provably efficient. Our proposed distributed learning framework features an effective gradient compression strategy and a worker-side model update design. We prove that the proposed communication-efficient distributed adaptive gradient method converges to the first-order stationary point with the same iteration complexity as uncompressed vanilla AMSGrad in the stochastic nonconvex optimization setting. Experiments on various benchmarks back up our theory.

6. AISTATS

   Communication-Compressed Adaptive Gradient Method for Distributed Nonconvex Optimization

   Yujia Wang, Lu Lin, and Jinghui Chen

   Proceedings of the 25th International Conference on Artificial Intelligence and Statistics, AISTATS 2022

   Abs arXiv HTML PDF

   Due to the explosion in the size of the training datasets, distributed learning has received growing interest in recent years. One of the major bottlenecks is the large communication cost between the central server and the local workers. While error feedback compression has been proven to be successful in reducing communication costs with stochastic gradient descent (SGD), there are much fewer attempts in building communication-efficient adaptive gradient methods with provable guarantees, which are widely used in training large-scale machine learning models. In this paper, we propose a new communication-compressed AMSGrad for distributed nonconvex optimization problem, which is provably efficient. Our proposed distributed learning framework features an effective gradient compression strategy and a worker-side model update design. We prove that the proposed communication-efficient distributed adaptive gradient method converges to the first-order stationary point with the same iteration complexity as uncompressed vanilla AMSGrad in the stochastic nonconvex optimization setting. Experiments on various benchmarks back up our theory.

7. WWW

   Unbiased Graph Embedding with Biased Graph Observations

   Nan Wang*, Lu Lin*, Jundong Li, and Hongning Wang

   Proceedings of the Web Conference, WWW 2022

   Abs arXiv HTML PDF Code

   Graph embedding techniques are pivotal in real-world machine learning tasks that operate on graph-structured data, such as social recommendation and protein structure modeling. Embeddings are mostly performed on the node level for learning representations of each node. Since the formation of a graph is inevitably affected by certain sensitive node attributes, the node embeddings can inherit such sensitive information and introduce undesirable biases in downstream tasks. Most existing works impose ad-hoc constraints on the node embeddings to restrict their distributions for unbiasedness/fairness, which however compromise the utility of the resulting embeddings. In this paper, we propose a principled new way for unbiased graph embedding by learning node embeddings from an underlying bias-free graph, which is not influenced by sensitive node attributes. Motivated by this new perspective, we propose two complementary methods for uncovering such an underlying graph, with the goal of introducing minimum impact on the utility of the embeddings. Both our theoretical justification and extensive experimental comparisons against state-of-the-art solutions demonstrate the effectiveness of our proposed methods.

8. KDD

   Graph Attention Networks over Edge Content-based Channels

   Lu Lin, and Hongning Wang

   In Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining, KDD 2020

   Abs HTML PDF Code Slides

   Edges play a crucial role in passing information on a graph, especially when they carry textual content reflecting semantics behind how nodes are linked and interacting with each other. In this paper, we propose a channel-aware attention mechanism enabled by edge text content when aggregating information from neighboring nodes; and we realize this mechanism in a graph autoencoder framework. Edge text content is encoded as low-dimensional mixtures of latent topics, which serve as semantic channels for topic-level information passing on edges. We embed nodes and topics in the same latent space to capture their mutual dependency when decoding the structural and textual information on graph. We evaluated the proposed model on Yelp user-item bipartite graph and StackOverflow user-user interaction graph. The proposed model outperformed a set of baselines on link prediction and content prediction tasks. Qualitative evaluations also demonstrated the descriptive power of the learnt node embeddings, showing its potential as an interpretable representation of graphs.

9. TKDE

   Road Traffic Speed Prediction: A Probabilistic Model Fusing Multi-source Data

   Lu Lin, Jianxin Li, Feng Chen, Jieping Ye, and Jinpeng Huai

   IEEE Transactions on Knowledge and Data Engineering, TKDE 2017

   Abs HTML PDF

   Road traffic speed prediction is a challenging problem in intelligent transportation system (ITS) and has gained increasing attentions. Existing works are mainly based on raw speed sensing data obtained from infrastructure sensors or probe vehicles, which, however, are limited by expensive cost of sensor deployment and maintenance. With sparse speed observations, traditional methods based only on speed sensing data are insufficient, especially when emergencies like traffic accidents occur. To address the issue, this paper aims to improve the road traffic speed prediction by fusing traditional speed sensing data with new-type “sensing” data from cross domain sources, such as tweet sensors from social media and trajectory sensors from map and traffic service platforms. Jointly modeling information from different datasets brings many challenges, including location uncertainty of low-resolution data, language ambiguity of traffic description in texts, and heterogeneity of cross-domain data. In response to these challenges, we present a unified probabilistic framework, called Topic-Enhanced Gaussian Process Aggregation Model (TEGPAM), consisting of three components, i.e., location disaggregation model, traffic topic model, and traffic speed Gaussian Process model, which integrate new-type data with traditional data. Experiments on real world data from two large cities validate the effectiveness and efficiency of our model.