Modern machine learning increasingly supports paradigms that are multi-institutional (using data from multiple institutions during training) or cross-institutional (using models from multiple institutions for inference), but the empirical effects of these paradigms are not well understood. This study investigates cross-institutional learning via an empirical case study in higher education. We propose a framework and metrics for assessing the utility and fairness of student dropout prediction models that are transferred across institutions. We examine the feasibility of cross-institutional transfer under real-world data- and model-sharing constraints, quantifying model biases for intersectional student identities, characterizing potential disparate impact due to these biases, and investigating the impact of various cross-institutional ensembling approaches on fairness and overall model performance. We perform this analysis on data representing over 200,000 enrolled students annually from four universities without sharing training data between institutions. We find that a simple zero-shot cross-institutional transfer procedure can achieve similar performance to locally-trained models for all institutions in our study, without sacrificing model fairness. We also find that stacked ensembling provides no additional benefits to overall performance or fairness compared to either a local model or the zero-shot transfer procedure we tested. We find no evidence of a fairness-accuracy tradeoff across dozens of models and transfer schemes evaluated. Our auditing procedure also highlights the importance of intersectional fairness analysis, revealing performance disparities at the intersection of sensitive identity groups that are concealed under one-dimensional analysis.

In this study we evaluate 32 unsupervised anomaly detection algorithms on 52 real-world multivariate tabular datasets, performing the largest comparison of unsupervised anomaly detection algorithms to date. On this collection of datasets, the $k$-thNN (distance to the $k$-nearest neighbor) algorithm significantly outperforms the most other algorithms. Visualizing and then clustering the relative performance of the considered algorithms on all datasets, we identify two clear clusters: one with ``local'' datasets, and another with ``global'' datasets. ``Local'' anomalies occupy a region with low density when compared to nearby samples, while ``global'' occupy an overall low density region in the feature space. On the local datasets the $k$NN ($k$-nearest neighbor) algorithm comes out on top. On the global datasets, the EIF (extended isolation forest) algorithm performs the best. Also taking into consideration the algorithms' computational complexity, a toolbox with these three unsupervised anomaly detection algorithms suffices for finding anomalies in this representative collection of multivariate datasets. By providing access to code and datasets, our study can be easily reproduced and extended with more algorithms and/or datasets.

The separation between training and deployment of machine learning models implies that not all scenarios encountered in deployment can be anticipated during training, and therefore relying solely on advancements in training has its limits. Out-of-distribution (OOD) detection is an important area that stress-tests a model's ability to handle unseen situations: Do models know when they don't know? Existing OOD detection methods either incur extra training steps, additional data or make nontrivial modifications to the trained network. In contrast, in this work, we propose an extremely simple, post-hoc, on-the-fly activation shaping method, ASH, where a large portion (e.g. The shaping is applied at inference time, and does not require any statistics calculated from training data. Experiments show that such a simple treatment enhances in-distribution and out-ofdistribution distinction so as to allow state-of-the-art OOD detection on ImageNet, and does not noticeably deteriorate the in-distribution accuracy. Video, animation and code can be found at: https://andrijazz.github.io/ash. Machine learning works by iteration. We develop better and better training techniques (validated in a closed-loop validation setting) and once a model is trained, we observe problems, shortcomings, pitfalls and misalignment in deployment, which drive us to go back to modify or refine the training process. However, as we enter an era of large models, recent progress is driven heavily by the advancement of scaling, seen on all fronts including the size of models, data, physical hardware as well as team of researchers and engineers (Kaplan et al., 2020; Brown et al., 2020; Ramesh et al., 2022; Saharia et al., 2022; Yu et al., 2022; Zhang et al., 2022). As a result, it is getting more difficult to conduct multiple iterations of the usual train-deployment loop; for that reason post hoc methods that improve model capability without the need to modify training are greatly preferred. Methods like zero-shot learning (Radford et al., 2021), plug-and-play controlling (Dathathri et al., 2020), as well as feature post processing (Guo et al., 2017) leverage post-hoc operations to make general and flexible pretrained models more adaptive to downstream applications. The out-of-distribution (OOD) generalization failure is one of such pitfalls often observed in deployment. The central question around OOD detection is "Do models know when they don't know?"

In prediction-based decision-making systems, different perspectives can be at odds: The short-term business goals of the decision makers are often in conflict with the decision subjects' wish to be treated fairly. Balancing these two perspectives is a question of values. However, these values are often hidden in the technicalities of the implementation of the decision-making system. In this paper, we propose a framework to make these value-laden choices clearly visible. We focus on a setting in which we want to find decision rules that balance the perspective of the decision maker and of the decision subjects. We provide an approach to formalize both perspectives, i.e., to assess the utility of the decision maker and the fairness towards the decision subjects. In both cases, the idea is to elicit values from decision makers and decision subjects that are then turned into something measurable. For the fairness evaluation, we build on well-known theories of distributive justice and on the algorithmic literature to ask what a fair distribution of utility (or welfare) looks like. This allows us to derive a fairness score that we then compare to the decision maker's utility. As we focus on a setting in which we are given a trained model and have to choose a decision rule, we use the concept of Pareto efficiency to compare decision rules. Our proposed framework can both guide the implementation of a decision-making system and help with audits, as it allows us to resurface the values implemented in a decision-making system.

Accurate bot detection is necessary for the safety and integrity of online platforms. It is also crucial for research on the influence of bots in elections, the spread of misinformation, and financial market manipulation. Platforms deploy infrastructure to flag or remove automated accounts, but their tools and data are not publicly available. Thus, the public must rely on third-party bot detection. These tools employ machine learning and often achieve near perfect performance for classification on existing datasets, suggesting bot detection is accurate, reliable and fit for use in downstream applications. We provide evidence that this is not the case and show that high performance is attributable to limitations in dataset collection and labeling rather than sophistication of the tools. Specifically, we show that simple decision rules -- shallow decision trees trained on a small number of features -- achieve near-state-of-the-art performance on most available datasets and that bot detection datasets, even when combined together, do not generalize well to out-of-sample datasets. Our findings reveal that predictions are highly dependent on each dataset's collection and labeling procedures rather than fundamental differences between bots and humans. These results have important implications for both transparency in sampling and labeling procedures and potential biases in research using existing bot detection tools for pre-processing.

Our work advances an approach for predicting hate speech in social media, drawing out the critical need to consider the discussions that follow a post to successfully detect when hateful discourse may arise. Using graph transformer networks, coupled with modelling attention and BERT-level natural language processing, our approach can capture context and anticipate upcoming anti-social behaviour. In this paper, we offer a detailed qualitative analysis of this solution for hate speech detection in social networks, leading to insights into where the method has the most impressive outcomes in comparison with competitors and identifying scenarios where there are challenges to achieving ideal performance. Included is an exploration of the kinds of posts that permeate social media today, including the use of hateful images. This suggests avenues for extending our model to be more comprehensive. A key insight is that the focus on reasoning about the concept of context positions us well to be able to support multi-modal analysis of online posts. We conclude with a reflection on how the problem we are addressing relates especially well to the theme of dynamic change, a critical concern for all AI solutions for social impact. We also comment briefly on how mental health well-being can be advanced with our work, through curated content attuned to the extent of hate in posts.

In this article I propose an approach for defining replicability for prediction rules. Motivated by a recent NAS report, I start from the perspective that replicability is obtaining consistent results across studies suitable to address the same prediction question, each of which has obtained its own data. I then discuss concept and issues in defining key elements of this statement. I focus specifically on the meaning of "consistent results" in typical utilization contexts, and propose a multi-agent framework for defining replicability, in which agents are neither partners nor adversaries. I recover some of the prevalent practical approaches as special cases. I hope to provide guidance for a more systematic assessment of replicability in machine learning.

Reliable multi-agent trajectory prediction is crucial for the safe planning and control of autonomous systems. Compared with single-agent cases, the major challenge in simultaneously processing multiple agents lies in modeling complex social interactions caused by various driving intentions and road conditions. Previous methods typically leverage graph-based message propagation or attention mechanism to encapsulate such interactions in the format of marginal probabilistic distributions. However, it is inherently sub-optimal. In this paper, we propose IPCC-TP, a novel relevance-aware module based on Incremental Pearson Correlation Coefficient to improve multi-agent interaction modeling. IPCC-TP learns pairwise joint Gaussian Distributions through the tightly-coupled estimation of the means and covariances according to interactive incremental movements. Our module can be conveniently embedded into existing multi-agent prediction methods to extend original motion distribution decoders. Extensive experiments on nuScenes and Argoverse 2 datasets demonstrate that IPCC-TP improves the performance of baselines by a large margin.

Globally, Coronary Heart Disease (CHD) is one of the main causes of death. Early detection of CHD can improve patient outcomes and reduce mortality rates. We propose a novel framework for predicting the presence of CHD using a combination of machine learning and image processing techniques. The framework comprises various phases, including analyzing the data, feature selection using ReliefF, 3D CNN-based segmentation, feature extraction by means of transfer learning, feature fusion as well as classification, and Adagrad optimization. The first step of the proposed framework involves analyzing the data to identify patterns and correlations that may be indicative of CHD. Next, ReliefF feature selection is applied to decide on the most relevant features from the sample images. The 3D CNN-based segmentation technique is then used to segment the optic disc and macula, which are important regions for CHD diagnosis. Feature extraction using transfer learning is performed to extract features from the segmented regions of interest. The extracted features are then fused using a feature fusion technique, and a classifier is trained to predict the presence of CHD. Finally, Adagrad optimization is used to optimize the performance of the classifier. Our framework is evaluated on a dataset of sample images collected from patients with and without CHD. The results show that the anticipated framework accomplishes elevated accuracy in predicting the presence of CHD. either a particular user with a reasonable degree of accuracy compared to the previously employed classifiers like SVM, etc.

To implement machine learning, it is essential to first determine an appropriate algorithm for the dataset. Different algorithms may produce a large number of different models with different hyperparameter configurations, and it usually takes a lot of time to run the model on a large dataset when the model is relatively complex. Therefore, how to predict the performance of a model on a dataset is an fundamental problem to be solved. This thesis designs a prediction system based on matrix factorization to predict the classification accuracy of a specific model on a particular dataset. In this thesis, we conduct a comprehensive empirical research on more than fifty datasets that we collected from the openml web site.