Vivian Lai
Vivian Lai has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Huiyuan Chen
Case Western Reserve University
9 shared publications - Chin-Chia Michael Yeh
Visa Research, Foster City, CA, USA
8 shared publications - Yan Zheng
Visa Research, Foster City, CA, USA
7 shared publications - Yujie Fan
Visa Research, Foster City, CA, USA
6 shared publications - Junpeng Wang
Visa Research, Foster City, CA, USA
5 shared publications - Liang Wang
Nanjing University
4 shared publications
Latest Publications
- Open Access
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 3719-3723
A Systematic Evaluation of Generated Time Series and Their Effects in Self-Supervised Pretraining
Self-supervised Pretrained Models (PTMs) have demonstrated remarkable performance in computer vision and natural language processing tasks. These successes have prompted researchers to design PTMs for time series data. In our experiments, most self-supervised time series PTMs were surpassed by simple supervised models. We hypothesize this undesired phenomenon may be caused by data scarcity. Our results indicate that replacing a real-data pretraining set with a greater volume of only generated samples produces noticeable improvement.
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 3719-3723
Open AccessA Systematic Evaluation of Generated Time Series and Their Effects in Self-Supervised Pretraining
Self-supervised Pretrained Models (PTMs) have demonstrated remarkable performance in computer vision and natural language processing tasks. These successes have prompted researchers to design PTMs for time series data. In our experiments, most self-supervised time series PTMs were surpassed by simple supervised models. We hypothesize this undesired phenomenon may be caused by data scarcity. Our results indicate that replacing a real-data pretraining set with a greater volume of only generated samples produces noticeable improvement.
- Open Access
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 3919-3930
RPMixer: Shaking Up Time Series Forecasting with Random Projections for Large Spatial-Temporal Data
Spatial-temporal forecasting systems play a crucial role in addressing numerous real-world challenges. In this paper, we investigate the potential of addressing spatial-temporal forecasting problems using general time series forecasting models, i.e., models that do not leverage the spatial relationships among the nodes. We propose a all-Multi-Layer Perceptron (all-MLP) time series forecasting architecture called RPMixer. The all-MLP architecture was chosen due to its recent success in time series forecasting benchmarks. Furthermore, our method capitalizes on the ensemble-like behavior of deep neural networks, where each individual block within the network behaves like a base learner in an ensemble model, particularly when identity mapping residual connections are incorporated. By integrating random projection layers into our model, we increase the diversity among the blocks' outputs, thereby improving the overall performance of the network. Extensive experiments conducted on the largest spatial-temporal forecasting benchmark datasets demonstrate that the proposed method outperforms 14 alternative methods.
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 3919-3930
Open AccessRPMixer: Shaking Up Time Series Forecasting with Random Projections for Large Spatial-Temporal Data
Spatial-temporal forecasting systems play a crucial role in addressing numerous real-world challenges. In this paper, we investigate the potential of addressing spatial-temporal forecasting problems using general time series forecasting models, i.e., models that do not leverage the spatial relationships among the nodes. We propose a all-Multi-Layer Perceptron (all-MLP) time series forecasting architecture called RPMixer. The all-MLP architecture was chosen due to its recent success in time series forecasting benchmarks. Furthermore, our method capitalizes on the ensemble-like behavior of deep neural networks, where each individual block within the network behaves like a base learner in an ensemble model, particularly when identity mapping residual connections are incorporated. By integrating random projection layers into our model, we increase the diversity among the blocks' outputs, thereby improving the overall performance of the network. Extensive experiments conducted on the largest spatial-temporal forecasting benchmark datasets demonstrate that the proposed method outperforms 14 alternative methods.
- Open Access
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 2502-2506
Masked Graph Transformer for Large-Scale Recommendation
Graph Transformers have garnered significant attention for learning graph-structured data, thanks to their superb ability to capture long-range dependencies among nodes. However, the quadratic space and time complexity hinders the scalability of Graph Transformers, particularly for large-scale recommendation. Here we propose an efficient Masked Graph Transformer, named MGFormer, capable of capturing all-pair interactions among nodes with a linear complexity. To achieve this, we treat all user/item nodes as independent tokens, enhance them with positional embeddings, and feed them into a kernelized attention module. Additionally, we incorporate learnable relative degree information to appropriately reweigh the attentions. Experimental results show the superior performance of our MGFormer, even with a single attention layer.
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 2502-2506
Open AccessMasked Graph Transformer for Large-Scale Recommendation
Graph Transformers have garnered significant attention for learning graph-structured data, thanks to their superb ability to capture long-range dependencies among nodes. However, the quadratic space and time complexity hinders the scalability of Graph Transformers, particularly for large-scale recommendation. Here we propose an efficient Masked Graph Transformer, named MGFormer, capable of capturing all-pair interactions among nodes with a linear complexity. To achieve this, we treat all user/item nodes as independent tokens, enhance them with positional embeddings, and feed them into a kernelized attention module. Additionally, we incorporate learnable relative degree information to appropriately reweigh the attentions. Experimental results show the superior performance of our MGFormer, even with a single attention layer.
- Open Access
- 4 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 106-115
Towards Mitigating Dimensional Collapse of Representations in Collaborative Filtering
Contrastive Learning (CL) has shown promising performance in collaborative filtering. The key idea is to use contrastive loss to generate augmentation-invariant embeddings by maximizing the Mutual Information between different augmented views of the same instance. However, we empirically observe that existing CL models suffer from the dimensional collapse issue, where user/item embeddings only span a low-dimension subspace of the entire feature space. This suppresses other dimensional information and weakens the distinguishability of embeddings. Here we propose a non-contrastive learning objective, named nCL, which explicitly mitigates dimensional collapse of representations in collaborative filtering. Our nCL aims to achieve geometric properties of Alignment and Compactness on the embedding space. In particular, the alignment tries to push together representations of positive-related user-item pairs, while compactness tends to find the optimal coding length of user/item embeddings, subject to a given distortion. More importantly, our nCL does not require data augmentation nor negative sampling during training, making it scalable to large datasets compared to contrastive learning methods. Experimental results demonstrate the superiority of our nCL.
- 4 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 106-115
Open AccessTowards Mitigating Dimensional Collapse of Representations in Collaborative Filtering
Contrastive Learning (CL) has shown promising performance in collaborative filtering. The key idea is to use contrastive loss to generate augmentation-invariant embeddings by maximizing the Mutual Information between different augmented views of the same instance. However, we empirically observe that existing CL models suffer from the dimensional collapse issue, where user/item embeddings only span a low-dimension subspace of the entire feature space. This suppresses other dimensional information and weakens the distinguishability of embeddings. Here we propose a non-contrastive learning objective, named nCL, which explicitly mitigates dimensional collapse of representations in collaborative filtering. Our nCL aims to achieve geometric properties of Alignment and Compactness on the embedding space. In particular, the alignment tries to push together representations of positive-related user-item pairs, while compactness tends to find the optimal coding length of user/item embeddings, subject to a given distortion. More importantly, our nCL does not require data augmentation nor negative sampling during training, making it scalable to large datasets compared to contrastive learning methods. Experimental results demonstrate the superiority of our nCL.
- Open Access
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 4400-4404
Toward a Foundation Model for Time Series Data
A foundation model is a machine learning model trained on a large and diverse set of data, typically using self-supervised learning-based pre-training techniques, that can be adapted to various downstream tasks. However, current research on time series pre-training has predominantly focused on models trained exclusively on data from a single domain. As a result, these models possess domain-specific knowledge that may not be easily transferable to time series from other domains. In this paper, we aim to develop an effective time series foundation model by leveraging unlabeled samples from multiple domains. To achieve this, we repurposed the publicly available UCR Archive and evaluated four existing self-supervised learning-based pre-training methods, along with a novel method, on the datasets. We tested these methods using four popular neural network architectures for time series to understand how the pre-training methods interact with different network designs. Our experimental results show that pre-training improves downstream classification tasks by enhancing the convergence of the fine-tuning process. Furthermore, we found that the proposed pre-training method, when combined with the Transformer, outperforms the alternatives. The proposed method outperforms or achieves equal performance compared to the second best method in ~93% of downstream tasks.
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 4400-4404
Open AccessToward a Foundation Model for Time Series Data
A foundation model is a machine learning model trained on a large and diverse set of data, typically using self-supervised learning-based pre-training techniques, that can be adapted to various downstream tasks. However, current research on time series pre-training has predominantly focused on models trained exclusively on data from a single domain. As a result, these models possess domain-specific knowledge that may not be easily transferable to time series from other domains. In this paper, we aim to develop an effective time series foundation model by leveraging unlabeled samples from multiple domains. To achieve this, we repurposed the publicly available UCR Archive and evaluated four existing self-supervised learning-based pre-training methods, along with a novel method, on the datasets. We tested these methods using four popular neural network architectures for time series to understand how the pre-training methods interact with different network designs. Our experimental results show that pre-training improves downstream classification tasks by enhancing the convergence of the fine-tuning process. Furthermore, we found that the proposed pre-training method, when combined with the Transformer, outperforms the alternatives. The proposed method outperforms or achieves equal performance compared to the second best method in ~93% of downstream tasks.
- Open Access
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 4909-4915
An Efficient Content-based Time Series Retrieval System
A Content-based Time Series Retrieval (CTSR) system is an information retrieval system for users to interact with time series emerged from multiple domains, such as finance, healthcare, and manufacturing. For example, users seeking to learn more about the source of a time series can submit the time series as a query to the CTSR system and retrieve a list of relevant time series with associated metadata. By analyzing the retrieved metadata, users can gather more information about the source of the time series. Because the CTSR system is required to work with time series data from diverse domains, it needs a high-capacity model to effectively measure the similarity between different time series. On top of that, the model within the CTSR system has to compute the similarity scores in an efficient manner as the users interact with the system in real-time. In this paper, we propose an effective and efficient CTSR model that outperforms alternative models, while still providing reasonable inference runtimes. To demonstrate the capability of the proposed method in solving business problems, we compare it against alternative models using our in-house transaction data. Our findings reveal that the proposed model is the most suitable solution compared to others for our transaction data problem.
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 4909-4915
Open AccessAn Efficient Content-based Time Series Retrieval System
A Content-based Time Series Retrieval (CTSR) system is an information retrieval system for users to interact with time series emerged from multiple domains, such as finance, healthcare, and manufacturing. For example, users seeking to learn more about the source of a time series can submit the time series as a query to the CTSR system and retrieve a list of relevant time series with associated metadata. By analyzing the retrieved metadata, users can gather more information about the source of the time series. Because the CTSR system is required to work with time series data from diverse domains, it needs a high-capacity model to effectively measure the similarity between different time series. On top of that, the model within the CTSR system has to compute the similarity scores in an efficient manner as the users interact with the system in real-time. In this paper, we propose an effective and efficient CTSR model that outperforms alternative models, while still providing reasonable inference runtimes. To demonstrate the capability of the proposed method in solving business problems, we compare it against alternative models using our in-house transaction data. Our findings reveal that the proposed model is the most suitable solution compared to others for our transaction data problem.
- Open Access
- 28 September 2023
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 7 (CSCW2) , 1-35
Selective Explanations: Leveraging Human Input to Align Explainable AI
While a vast collection of explainable AI (XAI) algorithms has been developed in recent years, they have been criticized for significant gaps with how humans produce and consume explanations. As a result, current XAI techniques are often found to be hard to use and lack effectiveness. In this work, we attempt to close these gaps by making AI explanations selective ---a fundamental property of human explanations---by selectively presenting a subset of model reasoning based on what aligns with the recipient's preferences. We propose a general framework for generating selective explanations by leveraging human input on a small dataset. This framework opens up a rich design space that accounts for different selectivity goals, types of input, and more. As a showcase, we use a decision-support task to explore selective explanations based on what the decision-maker would consider relevant to the decision task. We conducted two experimental studies to examine three paradigms based on our proposed framework: in Study 1, we ask the participants to provide critique-based or open-ended input to generate selective explanations (self-input). In Study 2, we show the participants selective explanations based on input from a panel of similar users (annotator input). Our experiments demonstrate the promise of selective explanations in reducing over-reliance on AI and improving collaborative decision making and subjective perceptions of the AI system, but also paint a nuanced picture that attributes some of these positive effects to the opportunity to provide one's own input to augment AI explanations. Overall, our work proposes a novel XAI framework inspired by human communication behaviors and demonstrates its potential to encourage future work to make AI explanations more human-compatible.
- 28 September 2023
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 7 (CSCW2) , 1-35
Open AccessSelective Explanations: Leveraging Human Input to Align Explainable AI
While a vast collection of explainable AI (XAI) algorithms has been developed in recent years, they have been criticized for significant gaps with how humans produce and consume explanations. As a result, current XAI techniques are often found to be hard to use and lack effectiveness. In this work, we attempt to close these gaps by making AI explanations selective ---a fundamental property of human explanations---by selectively presenting a subset of model reasoning based on what aligns with the recipient's preferences. We propose a general framework for generating selective explanations by leveraging human input on a small dataset. This framework opens up a rich design space that accounts for different selectivity goals, types of input, and more. As a showcase, we use a decision-support task to explore selective explanations based on what the decision-maker would consider relevant to the decision task. We conducted two experimental studies to examine three paradigms based on our proposed framework: in Study 1, we ask the participants to provide critique-based or open-ended input to generate selective explanations (self-input). In Study 2, we show the participants selective explanations based on input from a panel of similar users (annotator input). Our experiments demonstrate the promise of selective explanations in reducing over-reliance on AI and improving collaborative decision making and subjective perceptions of the AI system, but also paint a nuanced picture that attributes some of these positive effects to the opportunity to provide one's own input to augment AI explanations. Overall, our work proposes a novel XAI framework inspired by human communication behaviors and demonstrates its potential to encourage future work to make AI explanations more human-compatible.
- Open Access
- 14 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 245-255
Adversarial Collaborative Filtering for Free
- 14 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 245-255
Open AccessAdversarial Collaborative Filtering for Free
- Open Access
- 14 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 791-797
Enhancing Transformers without Self-supervised Learning: A Loss Landscape Perspective in Sequential Recommendation
Transformer and its variants are a powerful class of architectures for sequential recommendation, owing to their ability of capturing a user’s dynamic interests from their past interactions. Despite their success, Transformer-based models often require the optimization of a large number of parameters, making them difficult to train from sparse data in sequential recommendation. To address the problem of data sparsity, previous studies have utilized self-supervised learning to enhance Transformers, such as pre-training embeddings from item attributes or contrastive data augmentations. However, these approaches encounter several training issues, including initialization sensitivity, manual data augmentations, and large batch-size memory bottlenecks. In this work, we investigate Transformers from the perspective of loss geometry, aiming to enhance the models’ data efficiency and generalization in sequential recommendation. We observe that Transformers (e.g., SASRec) can converge to extremely sharp local minima if not adequately regularized. Inspired by the recent Sharpness-Aware Minimization (SAM), we propose SAMRec, which significantly improves the accuracy and robustness of sequential recommendation. SAMRec performs comparably to state-of-the-art self-supervised Transformers, such as S3Rec and CL4SRec, without the need for pre-training or strong data augmentations.
- 14 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 791-797
Open AccessEnhancing Transformers without Self-supervised Learning: A Loss Landscape Perspective in Sequential Recommendation
Transformer and its variants are a powerful class of architectures for sequential recommendation, owing to their ability of capturing a user’s dynamic interests from their past interactions. Despite their success, Transformer-based models often require the optimization of a large number of parameters, making them difficult to train from sparse data in sequential recommendation. To address the problem of data sparsity, previous studies have utilized self-supervised learning to enhance Transformers, such as pre-training embeddings from item attributes or contrastive data augmentations. However, these approaches encounter several training issues, including initialization sensitivity, manual data augmentations, and large batch-size memory bottlenecks. In this work, we investigate Transformers from the perspective of loss geometry, aiming to enhance the models’ data efficiency and generalization in sequential recommendation. We observe that Transformers (e.g., SASRec) can converge to extremely sharp local minima if not adequately regularized. Inspired by the recent Sharpness-Aware Minimization (SAM), we propose SAMRec, which significantly improves the accuracy and robustness of sequential recommendation. SAMRec performs comparably to state-of-the-art self-supervised Transformers, such as S3Rec and CL4SRec, without the need for pre-training or strong data augmentations.
- Open Access
- 18 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 2369-2373
Sharpness-Aware Graph Collaborative Filtering
Graph Neural Networks (GNNs) have achieved impressive performance in collaborative filtering. However, recent studies show that GNNs tend to yield inferior performance when the distributions of training and test data are not aligned well. Moreover, training GNNs often requires optimizing non-convex neural networks with an abundance of local and global minima, which may differ widely in their performance at test time. Thus, it is essential to develop an optimization strategy that can choose the minima carefully, which can yield strong generalization performance on unseen data. Here we propose an effective training schema, called gSAM, under the principle that theflatter minima has a better generalization ability than thesharper ones. To achieve this goal, gSAM regularizes the flatness of the weight loss landscape by forming a bi-level optimization: the outer problem conducts the standard model training while the inner problem helps the model jump out of the sharp minima. Experimental results show the superiority of our gSAM.
- 18 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 2369-2373
Open AccessSharpness-Aware Graph Collaborative Filtering
Graph Neural Networks (GNNs) have achieved impressive performance in collaborative filtering. However, recent studies show that GNNs tend to yield inferior performance when the distributions of training and test data are not aligned well. Moreover, training GNNs often requires optimizing non-convex neural networks with an abundance of local and global minima, which may differ widely in their performance at test time. Thus, it is essential to develop an optimization strategy that can choose the minima carefully, which can yield strong generalization performance on unseen data. Here we propose an effective training schema, called gSAM, under the principle that theflatter minima has a better generalization ability than thesharper ones. To achieve this goal, gSAM regularizes the flatness of the weight loss landscape by forming a bi-level optimization: the outer problem conducts the standard model training while the inner problem helps the model jump out of the sharp minima. Experimental results show the superiority of our gSAM.