In online advertising, marketing mix modeling (MMM) is employed to predict the gross merchandise volume (GMV) of brand shops and help decision-makers to adjust the budget allocation of various advertising channels. Traditional MMM methods leveraging regression techniques can fail in handling the complexity of marketing. Although some efforts try to encode the causal structures for better prediction, they have the strict restriction that causal structures are prior-known and unchangeable. In this paper, we define a new causal MMM problem that automatically discovers the interpretable causal structures from data and yields better GMV predictions. To achieve causal MMM, two essential challenges should be addressed: (1) Causal Heterogeneity. The causal structures of different kinds of shops vary a lot. (2) Marketing Response Patterns. Various marketing response patterns i.e., carryover effect and shape effect, have been validated in practice. We argue that causal MMM needs dynamically discover specific causal structures for different shops and the predictions should comply with the prior known marketing response patterns. Thus, we propose CausalMMM that integrates Granger causality in a variational inference framework to measure the causal relationships between different channels and predict the GMV with the regularization of both temporal and saturation marketing response patterns. Extensive experiments show that CausalMMM can not only achieve superior performance of causal structure learning on synthetic datasets with improvements of 5.7%\sim 7.1%, but also enhance the GMV prediction results on a representative E-commerce platform.

In the field of dynamic functional connectivity, the sliding-window method is widely used and its stability is generally recognized. However, the sliding-window method's data processing within the window is overly simplistic, which to some extent limits its effectiveness. This study proposes a feature expansion method based on random convolution, which achieves better and more noise-resistant results than the sliding-window method without requiring training. Experiments on simulated data show that the dynamic functional connectivity matrix and time series obtained using the random convolution method have a higher degree of fit (95.59\%) with the standard answers within shorter time windows, compared to the sliding-window method (45.99\%). Gender difference studies on real data also reveal that the random convolution method uncovers more gender differences than the sliding-window method. Through theoretical analysis, we propose a more comprehensive convolutional functional connectivity computation model, with the sliding-window method being a special case of this model, thereby opening up vast potential for research methods in dynamic functional connectivity.

We consider the problem of analyzing multivariate time series collected on multiple subjects, with the goal of identifying groups of subjects exhibiting similar trends in their recorded measurements over time as well as time-varying groups of associated measurements. To this end, we propose a Bayesian model for temporal biclustering featuring nested partitions, where a time-invariant partition of subjects induces a time-varying partition of measurements. Our approach allows for data-driven determination of the number of subject and measurement clusters as well as estimation of the number and location of changepoints in measurement partitions. To efficiently perform model fitting and posterior estimation with Markov Chain Monte Carlo, we derive a blocked update of measurements' cluster-assignment sequences. We illustrate the performance of our model in two applications to functional magnetic resonance imaging data and to an electroencephalogram dataset. The results indicate that the proposed model can combine information from potentially many subjects to discover a set of interpretable, dynamic patterns. Experiments on simulated data compare the estimation performance of the proposed model against ground-truth values and other statistical methods, showing that it performs well at identifying ground-truth subject and measurement clusters even when no subject or time dependence is present.

Dynamic pricing, the practice of adjusting prices based on contextual factors, has gained significant attention due to its impact on revenue maximization. In this paper, we address the contextual dynamic pricing problem, which involves pricing decisions based on observable product features and customer characteristics. We propose a novel algorithm that achieves improved regret bounds while minimizing assumptions about the problem. Our algorithm discretizes the unknown noise distribution and combines the upper confidence bounds with a layered data partitioning technique to effectively regulate regret in each episode. These techniques effectively control the regret associated with pricing decisions, leading to the minimax optimality. Specifically, our algorithm achieves a regret upper bound of $\tilde{\mathcal{O}}(\rho_{\mathcal{V}}^{\frac{1}{3}}(\delta) T^{\frac{2}{3}})$, where $\rho_{\mathcal{V}}(\delta)$ represents the estimation error of the valuation function. Importantly, this bound matches the lower bound up to logarithmic terms, demonstrating the minimax optimality of our approach. Furthermore, our method extends beyond linear valuation models commonly used in dynamic pricing by considering general function spaces. We simplify the estimation process by reducing it to general offline regression oracles, making implementation more straightforward.

This paper considers "model diagnosis", which we formulate as a classification problem. Given a pre-trained neural network (NN), the goal is to predict the source of failure from a set of failure modes (such as a wrong hyperparameter, inadequate model size, and insufficient data) without knowing the training configuration of the pre-trained NN. The conventional diagnosis approach uses training and validation errors to determine whether the model is underfitting or overfitting. However, we show that rich information about NN performance is encoded in the optimization loss landscape, which provides more actionable insights than validation-based measurements. Therefore, we propose a diagnosis method called MD tree based on loss landscape metrics and experimentally demonstrate its advantage over classical validation-based approaches. We verify the effectiveness of MD tree in multiple practical scenarios: (1) use several models trained on one dataset to diagnose a model trained on another dataset, essentially a few-shot dataset transfer problem; (2) use small models (or models trained with small data) to diagnose big models (or models trained with big data), essentially a scale transfer problem. In a dataset transfer task, MD tree achieves an accuracy of 87.7%, outperforming validation-based approaches by 14.88%. Our code is available at https://github.com/YefanZhou/ModelDiagnosis.

Predictive models may generate biased predictions when classifying imbalanced datasets. This happens when the model favors the majority class, leading to low performance in accurately predicting the minority class. To address this issue, balancing or resampling methods are critical pre-processing steps in the modeling process. However, there have been debates and questioning of the functionality of these methods in recent years. In particular, many candidate models may exhibit very similar predictive performance, which is called the Rashomon effect, in model selection. Selecting one of them without considering predictive multiplicity which is the case of yielding conflicting models' predictions for any sample may lead to a loss of using another model. In this study, in addition to the existing debates, the impact of balancing methods on predictive multiplicity is examined through the Rashomon effect. It is important because the blind model selection is risky from a set of approximately equally accurate models. This may lead to serious problems in model selection, validation, and explanation. To tackle this matter, we conducted real dataset experiments to observe the impact of balancing methods on predictive multiplicity through the Rashomon effect. Our findings showed that balancing methods inflate the predictive multiplicity, and they yield varying results. To monitor the trade-off between performance and predictive multiplicity for conducting the modeling process responsibly, we proposed using the extended performance-gain plot for the Rashomon effect.

Machine learning methods for estimating heterogeneous treatment effects (HTE) facilitate large-scale personalized decision-making across various domains such as healthcare, policy making, education, and more. Current machine learning approaches for HTE require access to substantial amounts of data per treatment, and the high costs associated with interventions makes centrally collecting so much data for each intervention a formidable challenge. To overcome this obstacle, in this work, we propose a novel framework for collaborative learning of HTE estimators across institutions via Federated Learning. We show that even under a diversity of interventions and subject populations across clients, one can jointly learn a common feature representation, while concurrently and privately learning the specific predictive functions for outcomes under distinct interventions across institutions. Our framework and the associated algorithm are based on this insight, and leverage tabular transformers to map multiple input data to feature representations which are then used for outcome prediction via multi-task learning. We also propose a novel way of federated training of personalised transformers that can work with heterogeneous input feature spaces. Experimental results on real-world clinical trial data demonstrate the effectiveness of our method.

The modelling of temporal patterns in dynamic graphs is an important current research issue in the development of time-aware GNNs. Whether or not a specific sequence of events in a temporal graph constitutes a temporal pattern not only depends on the frequency of its occurrence. We consider whether it deviates from what is expected in a temporal graph where timestamps are randomly shuffled. While accounting for such a random baseline is important to model temporal patterns, it has mostly been ignored by current temporal graph neural networks. To address this issue we propose HYPA-DBGNN, a novel two-step approach that combines (i) the inference of anomalous sequential patterns in time series data on graphs based on a statistically principled null model, with (ii) a neural message passing approach that utilizes a higher-order De Bruijn graph whose edges capture overrepresented sequential patterns. Our method leverages hypergeometric graph ensembles to identify anomalous edges within both first- and higher-order De Bruijn graphs, which encode the temporal ordering of events. The model introduces an inductive bias that enhances model interpretability. We evaluate our approach for static node classification using benchmark datasets and a synthetic dataset that showcases its ability to incorporate the observed inductive bias regarding over- and under-represented temporal edges. We demonstrate the framework's effectiveness in detecting similar patterns within empirical datasets, resulting in superior performance compared to baseline methods in node classification tasks. To the best of our knowledge, our work is the first to introduce statistically informed GNNs that leverage temporal and causal sequence anomalies. HYPA-DBGNN represents a path for bridging the gap between statistical graph inference and neural graph representation learning, with potential applications to static GNNs.

Out-of-distribution (OOD) detection methods have been developed to identify objects that a model has not seen during training. The Outlier Exposure (OE) methods use auxiliary datasets to train OOD detectors directly. However, the collection and learning of representative OOD samples may pose challenges. To tackle these issues, we propose the Outlier Aware Metric Learning (OAML) framework. The main idea of our method is to use the k-NN algorithm and Stable Diffusion model to generate outliers for training at the feature level without making any distributional assumptions. To increase feature discrepancies in the semantic space, we develop a mutual information-based contrastive learning approach for learning from OOD data effectively. Both theoretical and empirical results confirm the effectiveness of this contrastive learning technique. Furthermore, we incorporate knowledge distillation into our learning framework to prevent degradation of in-distribution classification accuracy. The combination of contrastive learning and knowledge distillation algorithms significantly enhances the performance of OOD detection. Experimental results across various datasets show that our method significantly outperforms previous OE methods.

Leveraging the models' outputs, specifically the logits, is a common approach to estimating the test accuracy of a pre-trained neural network on out-of-distribution (OOD) samples without requiring access to the corresponding ground truth labels. Despite their ease of implementation and computational efficiency, current logit-based methods are vulnerable to overconfidence issues, leading to prediction bias, especially under the natural shift. In this work, we first study the relationship between logits and generalization performance from the view of low-density separation assumption. Our findings motivate our proposed method MaNo which (1) applies a data-dependent normalization on the logits to reduce prediction bias, and (2) takes the $L_p$ norm of the matrix of normalized logits as the estimation score. Our theoretical analysis highlights the connection between the provided score and the model's uncertainty. We conduct an extensive empirical study on common unsupervised accuracy estimation benchmarks and demonstrate that MaNo achieves state-of-the-art performance across various architectures in the presence of synthetic, natural, or subpopulation shifts.