228 citations · 813 across the 67 of their papers we have counts for
48 papers · 1 filter
From Data to Program: Fast & Direct Generative Program Inference from Empirical Data
Simon Klüttermann, Xueying Ding, Leman Akoglu
Estimating probability densities from a finite set of samples typically requires dataset-specific model fitting. We introduce PRODiGI, a pretrained data-to-program model that infer…
When Less Compute Is More: Adaptive Early Exit Improves Pretrained Outlier Detection
Tianyang Zhou, Leman Akoglu
Pretrained tabular foundation models process every dataset at a fixed depth, with inference costs growing with dataset size. To address this, we present the first study of depth-ad…
TANGCO: Learning Topology-Aware Capacity Allocation for Overload-driven Cascading Failures
Orkun Irsoy, Leman Akoglu, Osman Yagan
Networked systems, from power grids to traffic networks and cloud clusters, carry loads across nodes with limited capacity. A node whose load exceeds its capacity fails and sheds i…
Activation Steering for Synthetic Data Generation: The Role of Diversity in Downstream Safety Detection
Vijeta Deshpande, Tootiya Giyahchi, Veena Padmanabhan +2
Safety detection models require examples of HHH (Helpful, Harmless, Honest)-violating outputs for robust generalization, however such examples are scarce. Activation Steering (AS)…
Toward Privileged Foundation Models:LUPI for Accelerated and Improved Learning
Xueying Ding, Leman Akoglu
Training foundation models is computationally intensive and often slow to converge. We introduce PIQL,Privileged Information for Quick and Quality Learning, the first framework to…
VIP-COP: Context Optimization for Tabular Foundation Models
Yilong Chen, Xueying Ding, Leman Akoglu
Tabular foundation models (TFMs) have emerged as a powerful paradigm for in-context learning on structured data, enabling direct prediction on new tabular tasks without task-specif…
MacrOData: New Benchmarks of Thousands of Datasets for Tabular Outlier Detection
Xueying Ding, Simon Klüttermann, Haomin Wen +2
Quality benchmarks are essential for fairly and accurately tracking scientific progress and enabling practitioners to make informed methodological choices. Outlier detection (OD) o…
From Zero to Hero: Advancing Zero-Shot Foundation Models for Tabular Outlier Detection
Xueying Ding, Haomin Wen, Simon Klüttermann +1
Outlier detection (OD) is widely used in practice; but its effective deployment on new tasks is hindered by lack of labeled outliers, which makes algorithm and hyperparameter selec…
Mitra: Mixed Synthetic Priors for Enhancing Tabular Foundation Models
Xiyuan Zhang, Danielle C. Maddix, Junming Yin +11
Since the seminal work of TabPFN, research on tabular foundation models (TFMs) based on in-context learning (ICL) has challenged long-standing paradigms in machine learning. Withou…
CoBAD: Modeling Collective Behaviors for Human Mobility Anomaly Detection
Haomin Wen, Shurui Cao, Leman Akoglu
Detecting anomalies in human mobility is essential for applications such as public safety and urban planning. While traditional anomaly detection methods primarily focus on individ…
FoMo-0D: A Foundation Model for Zero-shot Tabular Outlier Detection
Yuchen Shen, Haomin Wen, Leman Akoglu
Outlier detection (OD) has a vast literature as it finds numerous real-world applications. Being an unsupervised task, model selection is a key bottleneck for OD without label supe…
Outlier Detection Bias Busted: Understanding Sources of Algorithmic Bias through Data-centric Factors
Xueying Ding, Rui Xi, Leman Akoglu
The astonishing successes of ML have raised growing concern for the fairness of modern methods when deployed in real world settings. However, studies on fairness have mostly focuse…
End-To-End Self-Tuning Self-Supervised Time Series Anomaly Detection
Boje Deforce, Meng-Chieh Lee, Bart Baesens +3
Time series anomaly detection (TSAD) finds many applications such as monitoring environmental sensors, industry KPIs, patient biomarkers, etc. A two-fold challenge for TSAD is a ve…
Descriptive Kernel Convolution Network with Improved Random Walk Kernel
Meng-Chieh Lee, Lingxiao Zhao, Leman Akoglu
Graph kernels used to be the dominant approach to feature engineering for structured data, which are superseded by modern GNNs as the former lacks learnability. Recently, a suite o…
Unified Discrete Diffusion for Categorical Data
Lingxiao Zhao, Xueying Ding, Lijun Yu +1
Discrete diffusion models have seen a surge of attention with applications on naturally discrete data such as language and graphs. Although discrete-time discrete diffusion has bee…
Pard: Permutation-Invariant Autoregressive Diffusion for Graph Generation
Lingxiao Zhao, Xueying Ding, Leman Akoglu
Graph generation has been dominated by autoregressive models due to their simplicity and effectiveness, despite their sensitivity to ordering. Yet diffusion models have garnered in…
ADAMM: Anomaly Detection of Attributed Multi-graphs with Metadata: A Unified Neural Network Approach
Konstantinos Sotiropoulos, Lingxiao Zhao, Pierre Jinghong Liang +1
Given a complex graph database of node- and edge-attributed multi-graphs as well as associated metadata for each graph, how can we spot the anomalous instances? Many real-world pro…
Self-Supervision for Tackling Unsupervised Anomaly Detection: Pitfalls and Opportunities
Leman Akoglu, Jaemin Yoo
Self-supervised learning (SSL) is a growing torrent that has recently transformed machine learning and its many real world applications, by learning on massive amounts of unlabeled…
DSV: An Alignment Validation Loss for Self-supervised Outlier Model Selection
Jaemin Yoo, Yue Zhao, Lingxiao Zhao +1
Self-supervised learning (SSL) has proven effective in solving various problems by generating internal supervisory signals. Unsupervised anomaly detection, which faces the high cos…
Fast Unsupervised Deep Outlier Model Selection with Hypernetworks
Xueying Ding, Yue Zhao, Leman Akoglu
Outlier detection (OD) finds many applications with a rich literature of numerous techniques. Deep neural network based OD (DOD) has seen a recent surge of attention thanks to the…
Self-Tuning Self-Supervised Image Anomaly Detection
Jaemin Yoo, Lingxiao Zhao, Leman Akoglu
Self-supervised learning (SSL) has emerged as a promising paradigm that presents supervisory signals to real-world problems, bypassing the extensive cost of manual labeling. Conseq…
From Explanation to Action: An End-to-End Human-in-the-loop Framework for Anomaly Reasoning and Management
Xueying Ding, Nikita Seleznev, Senthil Kumar +2
Anomalies are often indicators of malfunction or inefficiency in various systems such as manufacturing, healthcare, finance, surveillance, to name a few. While the literature is ab…
Toward Unsupervised Outlier Model Selection
Yue Zhao, Sean Zhang, Leman Akoglu
Today there exists no shortage of outlier detection algorithms in the literature, yet the complementary and critical problem of unsupervised outlier model selection (UOMS) is vastl…
A Practical, Progressively-Expressive GNN
Lingxiao Zhao, Louis Härtel, Neil Shah +1
Message passing neural networks (MPNNs) have become a dominant flavor of graph neural networks (GNNs) in recent years. Yet, MPNNs come with notable limitations; namely, they are at…