Vivian Lai

Vivian Lai

Auto-generated profile, based on publicly available information

Vivian Lai

Visa Research, Foster City, CA, USA

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications

28 September 2023 in Proceedings of the ACM on Human-Computer Interaction
Verified
Journal Article
Open access
VLVivian Lai
Vivian Lai
YZYiming Zhang
Yiming Zhang
CCChacha Chen
Chacha Chen
QLQ. Vera Liao
Q. Vera Liao
CTChenhao Tan
Chenhao Tan
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.

21 October 2023
Verified
Conference Paper
Open access
CYChin-Chia Michael Yeh
Chin-Chia Michael Yeh
XDXin Dai
Xin Dai
HCHuiyuan Chen
Huiyuan Chen
YZYan Zheng
Yan Zheng
YFYujie Fan
Yujie Fan
WZWei Zhang
Wei Zhang
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.

4 March 2024
Verified
Conference Paper
Open access
HCHuiyuan Chen
Huiyuan Chen
VLVivian Lai
Vivian Lai
HJHongye Jin
Hongye Jin
ZJZhimeng Jiang
Zhimeng Jiang
MDMahashweta Das
Mahashweta Das
XHXia Hu
Xia Hu
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.

10 July 2024
Verified
Conference Paper
Open access
HCHuiyuan Chen
Huiyuan Chen
ZXZhe Xu
Zhe Xu
CYChin-Chia Michael Yeh
Chin-Chia Michael Yeh
VLVivian Lai
Vivian Lai
YZYan Zheng
Yan Zheng
HTHanghang Tong
Hanghang Tong
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.

24 August 2024
Verified
Conference Paper
Open access
CYChin-Chia Michael Yeh
Chin-Chia Michael Yeh
YFYujie Fan
Yujie Fan
XDXin Dai
Xin Dai
USUday Singh Saini
Uday Singh Saini
VLVivian Lai
Vivian Lai
WZWei Zhang
Wei Zhang
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.