Search Results for author:
Found 153 papers, 89 papers with code
$χ$SPN: Characteristic Interventional Sum-Product Networks for Causal Inference in Hybrid Domains
Causal inference in hybrid domains, characterized by a mixture of discrete and continuous variables, presents a formidable challenge.
Problem Solving Through Human-AI Preference-Based Cooperation
While there is a widespread belief that artificial general intelligence (AGI) -- or even superhuman AI -- is imminent, complex problems in expert domains are far from being solved.
T-FREE: Tokenizer-Free Generative LLMs via Sparse Representations for Memory-Efficient Embeddings
Tokenizers are crucial for encoding information in Large Language Models, but their development has recently stagnated, and they contain inherent weaknesses.
OCALM: Object-Centric Assessment with Language Models
Properly defining a reward signal to efficiently train a reinforcement learning (RL) agent is a challenging task.
Neural Concept Binder
The challenge in object-based visual reasoning lies in generating descriptive yet distinct concept representations.
EXPIL: Explanatory Predicate Invention for Learning in Games
In this work, we propose a novel approach, Explanatory Predicate Invention for Learning in Games (EXPIL), that identifies and extracts predicates from a pretrained neural agent, later used in the logic-based agents, reducing the dependency on predefined background knowledge.
LLavaGuard: VLM-based Safeguards for Vision Dataset Curation and Safety Assessment
We introduce LlavaGuard, a family of VLM-based safeguard models, offering a versatile framework for evaluating the safety compliance of visual content.
HackAtari: Atari Learning Environments for Robust and Continual Reinforcement Learning
Overall, HackAtari can be used to improve the robustness of current and future RL algorithms, allowing Neuro-Symbolic RL, curriculum RL, causal RL, as well as LLM-driven RL.
Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models
Unfortunately, this practice raises privacy and intellectual property concerns, as DMs can memorize and later reproduce their potentially sensitive or copyrighted training images at inference time.
Interpretable and Editable Programmatic Tree Policies for Reinforcement Learning
We empirically demonstrate that INTERPRETER compact tree programs match oracles across a diverse set of sequential decision tasks and evaluate the impact of our design choices on interpretability and performances.
ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming
When building Large Language Models (LLMs), it is paramount to bear safety in mind and protect them with guardrails.
Mechanistic Design and Scaling of Hybrid Architectures
The development of deep learning architectures is a resource-demanding process, due to a vast design space, long prototyping times, and high compute costs associated with at-scale model training and evaluation.
Credibility-Aware Multi-Modal Fusion Using Probabilistic Circuits
We consider the problem of late multi-modal fusion for discriminative learning.
United We Pretrain, Divided We Fail! Representation Learning for Time Series by Pretraining on 75 Datasets at Once
Actually, common belief is that multi-dataset pretraining does not work for time series!
DeiSAM: Segment Anything with Deictic Prompting
To remedy this issue, we propose DeiSAM -- a combination of large pre-trained neural networks with differentiable logic reasoners -- for deictic promptable segmentation.
Right on Time: Revising Time Series Models by Constraining their Explanations
Feedback on explanations in both domains is then used to constrain the model, steering it away from the annotated confounding factors.
Exploring the Adversarial Capabilities of Large Language Models
The proliferation of large language models (LLMs) has sparked widespread and general interest due to their strong language generation capabilities, offering great potential for both industry and research.
Pix2Code: Learning to Compose Neural Visual Concepts as Programs
The challenge in learning abstract concepts from images in an unsupervised fashion lies in the required integration of visual perception and generalizable relational reasoning.
Amplifying Exploration in Monte-Carlo Tree Search by Focusing on the Unknown
It strategically allocates computational resources to focus on promising segments of the search tree, making it a very attractive search algorithm in large search spaces.
Where is the Truth? The Risk of Getting Confounded in a Continual World
In particular, we provide a formal description of such continual confounders and identify that, in general, spurious correlations are easily ignored when training for all tasks jointly, but it is harder to avoid confounding when they are considered sequentially.
BOWLL: A Deceptively Simple Open World Lifelong Learner
The quest to improve scalar performance numbers on predetermined benchmarks seems to be deeply engraved in deep learning.
Checkmating One, by Using Many: Combining Mixture of Experts with MCTS to Improve in Chess
This paper presents a new approach that integrates deep learning with computational chess, using both the Mixture of Experts (MoE) method and Monte-Carlo Tree Search (MCTS).
Multilingual Text-to-Image Generation Magnifies Gender Stereotypes and Prompt Engineering May Not Help You
Our results show that not only do models exhibit strong gender biases but they also behave differently across languages.
Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents
Unfortunately, the black-box nature of deep neural networks impedes the inclusion of domain experts for inspecting the model and revising suboptimal policies.
Characteristic Circuits
In many real-world scenarios, it is crucial to be able to reliably and efficiently reason under uncertainty while capturing complex relationships in data.
LEDITS++: Limitless Image Editing using Text-to-Image Models
Our results demonstrate the capabilities of LEDITS++ and its improvements over previous methods.
From Images to Connections: Can DQN with GNNs learn the Strategic Game of Hex?
The gameplay of strategic board games such as chess, Go and Hex is often characterized by combinatorial, relational structures -- capturing distinct interactions and non-local patterns -- and not just images.
Divergent Token Metrics: Measuring degradation to prune away LLM components -- and optimize quantization
Large Language Models (LLMs) have reshaped natural language processing with their impressive capabilities.
SPARE: A Single-Pass Neural Model for Relational Databases
While there has been extensive work on deep neural networks for images and text, deep learning for relational databases (RDBs) is still a rather unexplored field.
Defending Our Privacy With Backdoors
Our approach provides a new "dual-use" perspective on backdoor attacks and presents a promising avenue to enhance the privacy of individuals within models trained on uncurated web-scraped data.
Leveraging Diffusion-Based Image Variations for Robust Training on Poisoned Data
To address this challenge, we propose a novel approach that enables model training on potentially poisoned datasets by utilizing the power of recent diffusion models.
Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks
Label smoothing -- using softened labels instead of hard ones -- is a widely adopted regularization method for deep learning, showing diverse benefits such as enhanced generalization and calibration.
Distilling Adversarial Prompts from Safety Benchmarks: Report for the Adversarial Nibbler Challenge
Text-conditioned image generation models have recently achieved astonishing image quality and alignment results.
Learning by Self-Explaining
Current AI research mainly treats explanations as a means for model inspection.
Learning to Intervene on Concept Bottlenecks
To rectify this, we present concept bottleneck memory models (CB2Ms), which keep a memory of past interventions.
Causal Parrots: Large Language Models May Talk Causality But Are Not Causal
We conjecture that in the cases where LLM succeed in doing causal inference, underlying was a respective meta SCM that exposed correlations between causal facts in natural language on whose data the LLM was ultimately trained.
Balancing Transparency and Risk: The Security and Privacy Risks of Open-Source Machine Learning Models
The field of artificial intelligence (AI) has experienced remarkable progress in recent years, driven by the widespread adoption of open-source machine learning models in both research and industry.
Vision Relation Transformer for Unbiased Scene Graph Generation
Recent years have seen a growing interest in Scene Graph Generation (SGG), a comprehensive visual scene understanding task that aims to predict entity relationships using a relation encoder-decoder pipeline stacked on top of an object encoder-decoder backbone.
Self-Expanding Neural Networks
The results of training a neural network are heavily dependent on the architecture chosen; and even a modification of only its size, however small, typically involves restarting the training process.
Learning Differentiable Logic Programs for Abstract Visual Reasoning
However, due to the memory intensity, most existing approaches do not bring the best of the expressivity of first-order logic, excluding a crucial ability to solve abstract visual reasoning, where agents need to perform reasoning by using analogies on abstract concepts in different scenarios.
OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments
In our work, we extend the Atari Learning Environments, the most-used evaluation framework for deep RL approaches, by introducing OCAtari, that performs resource-efficient extractions of the object-centric states for these games.
Scalable Neural-Probabilistic Answer Set Programming
The goal of combining the robustness of neural networks and the expressiveness of symbolic methods has rekindled the interest in Neuro-Symbolic AI.
V-LoL: A Diagnostic Dataset for Visual Logical Learning
Despite the successes of recent developments in visual AI, different shortcomings still exist; from missing exact logical reasoning, to abstract generalization abilities, to understanding complex and noisy scenes.
ChatGPT is fun, but it is not funny! Humor is still challenging Large Language Models
In a series of exploratory experiments around jokes, i. e., generation, explanation, and detection, we seek to understand ChatGPT's capability to grasp and reproduce human humor.
Masked Autoencoders are Efficient Continual Federated Learners
In parts, federated learning lifts this assumption, as it sets out to solve the real-world challenge of collaboratively learning a shared model from data distributed across clients.
Deep Classifier Mimicry without Data Access
We posit that original data access may however not be required.
Mitigating Inappropriateness in Image Generation: Can there be Value in Reflecting the World's Ugliness?
Text-conditioned image generation models have recently achieved astonishing results in image quality and text alignment and are consequently employed in a fast-growing number of applications.
MultiFusion: Fusing Pre-Trained Models for Multi-Lingual, Multi-Modal Image Generation
The recent popularity of text-to-image diffusion models (DM) can largely be attributed to the intuitive interface they provide to users.
Know your Enemy: Investigating Monte-Carlo Tree Search with Opponent Models in Pommerman
In combination with Reinforcement Learning, Monte-Carlo Tree Search has shown to outperform human grandmasters in games such as Chess, Shogi and Go with little to no prior domain knowledge.
Representation Matters for Mastering Chess: Improved Feature Representation in AlphaZero Outperforms Switching to Transformers
While transformers have gained recognition as a versatile tool for artificial intelligence (AI), an unexplored challenge arises in the context of chess - a classical AI benchmark.
One Explanation Does Not Fit XIL
Current machine learning models produce outstanding results in many areas but, at the same time, suffer from shortcut learning and spurious correlations.
Class Attribute Inference Attacks: Inferring Sensitive Class Information by Diffusion-Based Attribute Manipulations
Neural network-based image classifiers are powerful tools for computer vision tasks, but they inadvertently reveal sensitive attribute information about their classes, raising concerns about their privacy.
Probabilistic Circuits That Know What They Don't Know
In contrast to neural networks, they are often assumed to be well-calibrated and robust to out-of-distribution (OOD) data.
Fair Diffusion: Instructing Text-to-Image Generation Models on Fairness
Generative AI models have recently achieved astonishing results in quality and are consequently employed in a fast-growing number of applications.
SEGA: Instructing Text-to-Image Models using Semantic Guidance
This leaves the user with little semantic control.
AtMan: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation
Generative transformer models have become increasingly complex, with large numbers of parameters and the ability to process multiple input modalities.
Pearl Causal Hierarchy on Image Data: Intricacies & Challenges
Many researchers have voiced their support towards Pearl's counterfactual theory of causation as a stepping stone for AI/ML research's ultimate goal of intelligent systems.
The Stable Artist: Steering Semantics in Diffusion Latent Space
Large, text-conditioned generative diffusion models have recently gained a lot of attention for their impressive performance in generating high-fidelity images from text alone.
Neural Meta-Symbolic Reasoning and Learning
To make deep learning do more from less, we propose the first neural meta-symbolic system (NEMESYS) for reasoning and learning: meta programming using differentiable forward-chaining reasoning in first-order logic.
Boosting Object Representation Learning via Motion and Object Continuity
Recent unsupervised multi-object detection models have shown impressive performance improvements, largely attributed to novel architectural inductive biases.
Speaking Multiple Languages Affects the Moral Bias of Language Models
Do the models capture moral norms from English and impose them on other languages?
Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models
Text-conditioned image generation models have recently achieved astonishing results in image quality and text alignment and are consequently employed in a fast-growing number of applications.
Rickrolling the Artist: Injecting Backdoors into Text Encoders for Text-to-Image Synthesis
We introduce backdoor attacks against text-guided generative models and demonstrate that their text encoders pose a major tampering risk.
Revision Transformers: Instructing Language Models to Change their Values
In this work, we question the current common practice of storing all information in the model parameters and propose the Revision Transformer (RiT) to facilitate easy model updating.
Exploiting Cultural Biases via Homoglyphs in Text-to-Image Synthesis
Models for text-to-image synthesis, such as DALL-E~2 and Stable Diffusion, have recently drawn a lot of interest from academia and the general public.
Does CLIP Know My Face?
Our large-scale experiments on CLIP demonstrate that individuals used for training can be identified with very high accuracy.
LogicRank: Logic Induced Reranking for Generative Text-to-Image Systems
Text-to-image models have recently achieved remarkable success with seemingly accurate samples in photo-realistic quality.
Combining AI and AM - Improving Approximate Matching through Transformer Networks
Then DLAM is able to detect the patterns in a typically much larger file, that is DLAM focuses on the use case of fragment detection.
ILLUME: Rationalizing Vision-Language Models through Human Interactions
Bootstrapping from pre-trained language models has been proven to be an efficient approach for building vision-language models (VLM) for tasks such as image captioning or visual question answering.
FEATHERS: Federated Architecture and Hyperparameter Search
Deep neural architectures have profound impact on achieved performance in many of today's AI tasks, yet, their design still heavily relies on human prior knowledge and experience.
Attributions Beyond Neural Networks: The Linear Program Case
We introduce an approach where we consider neural encodings for LPs that justify the application of attribution methods from explainable artificial intelligence (XAI) designed for neural learning systems.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
Towards a Solution to Bongard Problems: A Causal Approach
Even though AI has advanced rapidly in recent years displaying success in solving highly complex problems, the class of Bongard Problems (BPs) yet remain largely unsolved by modern ML techniques.
Tearing Apart NOTEARS: Controlling the Graph Prediction via Variance Manipulation
Simulations are ubiquitous in machine learning.
Machines Explaining Linear Programs
In this work, we extend the attribution methods for explaining neural networks to linear programs.
Can Foundation Models Talk Causality?
Foundation models are subject to an ongoing heated debate, leaving open the question of progress towards AGI and dividing the community into two camps: the ones who see the arguably impressive results as evidence to the scaling hypothesis, and the others who are worried about the lack of interpretability and reasoning capabilities.
Gradient-based Counterfactual Explanations using Tractable Probabilistic Models
Counterfactual examples are an appealing class of post-hoc explanations for machine learning models.
Adaptable Adapters
The resulting adapters (a) contain about 50% of the learning parameters of the standard adapter and are therefore more efficient at training and inference, and require less storage space, and (b) achieve considerably higher performances in low-data settings.
Finding Structure and Causality in Linear Programs
Linear Programs (LP) are celebrated widely, particularly so in machine learning where they have allowed for effectively solving probabilistic inference tasks or imposing structure on end-to-end learning systems.
Do Multilingual Language Models Capture Differing Moral Norms?
Massively multilingual sentence representations are trained on large corpora of uncurated data, with a very imbalanced proportion of languages included in the training.
A Typology for Exploring the Mitigation of Shortcut Behavior
In addition, we discuss existing and introduce novel measures and benchmarks for evaluating the overall abilities of a XIL method.
Neuro-Symbolic Verification of Deep Neural Networks
Formal verification has emerged as a powerful approach to ensure the safety and reliability of deep neural networks.
Can Machines Help Us Answering Question 16 in Datasheets, and In Turn Reflecting on Inappropriate Content?
This calls for increased dataset documentation, e. g., using datasheets.
Right for the Right Latent Factors: Debiasing Generative Models via Disentanglement
A key assumption of most statistical machine learning methods is that they have access to independent samples from the distribution of data they encounter at test time.
Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks
Model inversion attacks (MIAs) aim to create synthetic images that reflect the class-wise characteristics from a target classifier's private training data by exploiting the model's learned knowledge.
Interactive Disentanglement: Learning Concepts by Interacting with their Prototype Representations
In this work, we show the advantages of prototype representations for understanding and revising the latent space of neural concept learners.
To Trust or Not To Trust Prediction Scores for Membership Inference Attacks
Membership inference attacks (MIAs) aim to determine whether a specific sample was used to train a predictive model.
Learning to Break Deep Perceptual Hashing: The Use Case NeuralHash
Specifically, we show that current deep perceptual hashing may not be robust.
A Taxonomy for Inference in Causal Model Families
More specifically, there are models capable of answering causal queries that are not SCM, which we refer to as \emph{partially causal models} (PCM).
The Causal Loss: Driving Correlation to Imply Causation
Most algorithms in classical and contemporary machine learning focus on correlation-based dependence between features to drive performance.
Explaining Deep Tractable Probabilistic Models: The sum-product network case
We consider the problem of explaining a class of tractable deep probabilistic models, the Sum-Product Networks (SPNs) and present an algorithm ExSPN to generate explanations.
Neuro-Symbolic Forward Reasoning
NSFR factorizes the raw inputs into the object-centric representations, converts them into probabilistic ground atoms, and finally performs differentiable forward-chaining inference using weighted rules for inference.
Inferring Offensiveness In Images From Natural Language Supervision
Probing or fine-tuning (large-scale) pre-trained models results in state-of-the-art performance for many NLP tasks and, more recently, even for computer vision tasks when combined with image data.
CLEVA-Compass: A Continual Learning EValuation Assessment Compass to Promote Research Transparency and Comparability
What is the state of the art in continual machine learning?
SLASH: Embracing Probabilistic Circuits into Neural Answer Set Programming
The probability estimates resulting from NPPs act as the binding element between the logical program and raw input data, thereby allowing SLASH to answer task-dependent logical queries.
Causal Explanations of Structural Causal Models
The question part on the user's end we believe to be solved since the user's mental model can provide the causal model.
Sum-Product-Attention Networks: Leveraging Self-Attention in Probabilistic Circuits
Probabilistic circuits (PCs) have become the de-facto standard for learning and inference in probabilistic modeling.
DAFNe: A One-Stage Anchor-Free Approach for Oriented Object Detection
We present DAFNe, a Dense one-stage Anchor-Free deep Network for oriented object detection.
Ranked #3 on
Oriented Object Detection
on DOTA 1.5
Relating Graph Neural Networks to Structural Causal Models
Causality can be described in terms of a structural causal model (SCM) that carries information on the variables of interest and their mechanistic relations.
Interactively Providing Explanations for Transformer Language Models
Transformer language models are state of the art in a multitude of NLP tasks.
Generative Adversarial Neural Cellular Automata
Motivated by the interaction between cells, the recently introduced concept of Neural Cellular Automata shows promising results in a variety of tasks.
Leveraging Probabilistic Circuits for Nonparametric Multi-Output Regression
Inspired by recent advances in the field of expert-based approximations of Gaussian processes (GPs), we present an expert-based approach to large-scale multi-output regression using single-output GP experts.
RECOWNs: Probabilistic Circuits for Trustworthy Time Series Forecasting
Time series forecasting is a relevant task that is performed in several real-world scenarios such as product sales analysis and prediction of energy demand.
Structural Causal Models Reveal Confounder Bias in Linear Program Modelling
The recent years have been marked by extended research on adversarial attacks, especially on deep neural networks.
User-Level Label Leakage from Gradients in Federated Learning
Specifically, we investigate Label Leakage from Gradients (LLG), a novel attack to extract the labels of the users' training data from their shared gradients.
Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentation
We present ObSuRF, a method which turns a single image of a scene into a 3D model represented as a set of Neural Radiance Fields (NeRFs), with each NeRF corresponding to a different object.
Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do
That is, we show that these norms can be captured geometrically by a direction, which can be computed, e. g., by a PCA, in the embedding space, reflecting well the agreement of phrases to social norms implicitly expressed in the training texts and providing a path for attenuating or even preventing toxic degeneration in LMs.
Interventional Sum-Product Networks: Causal Inference with Tractable Probabilistic Models
While probabilistic models are an important tool for studying causality, doing so suffers from the intractability of inference.
Adaptive Rational Activations to Boost Deep Reinforcement Learning
Latest insights from biology show that intelligence not only emerges from the connections between neurons but that individual neurons shoulder more computational responsibility than previously anticipated.
Ranked #3 on
Atari Games
on Atari 2600 Skiing
(using extra training data)
Monte-Carlo Graph Search for AlphaZero
The AlphaZero algorithm has been successfully applied in a range of discrete domains, most notably board games.
Rule Extraction from Binary Neural Networks with Convolutional Rules for Model Validation
Most deep neural networks are considered to be black boxes, meaning their output is hard to interpret.
Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting with their Explanations
Most explanation methods in deep learning map importance estimates for a model's prediction back to the original input space.
TUDataset: A collection of benchmark datasets for learning with graphs
We provide Python-based data loaders, kernel and graph neural network baseline implementations, and evaluation tools.
Fitted Q-Learning for Relational Domains
We consider the problem of Approximate Dynamic Programming in relational domains.
Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic Circuits
Probabilistic circuits (PCs) are a promising avenue for probabilistic modeling, as they permit a wide range of exact and efficient inference routines.
CryptoSPN: Privacy-preserving Sum-Product Network Inference
AI algorithms, and machine learning (ML) techniques in particular, are increasingly important to individuals' lives, but have caused a range of privacy concerns addressed by, e. g., the European GDPR.
Making deep neural networks right for the right scientific reasons by interacting with their explanations
Deep neural networks have shown excellent performances in many real-world applications.
BERT has a Moral Compass: Improvements of ethical and moral values of machines
But has BERT also a better moral compass?
Structured Object-Aware Physics Prediction for Video Modeling and Planning
When humans observe a physical system, they can easily locate objects, understand their interactions, and anticipate future behavior, even in settings with complicated and previously unseen interactions.
Meta-Learning Runge-Kutta
However, by studying the characteristics of the local error function we show that including the partial derivatives of the initial value problem is favorable.
DeepDB: Learn from Data, not from Queries!
The typical approach for learned DBMS components is to capture the behavior by running a representative set of queries and use the observations to train a machine learning model.
Databases
Neural Networks for Relational Data
While deep networks have been enormously successful over the last decade, they rely on flat-feature vector representations, which makes them unsuitable for richly structured domains such as those arising in applications like social network analysis.
Learning to play the Chess Variant Crazyhouse above World Champion Level with Deep Neural Networks and Human Data
Crazyhouse is a game with a higher branching factor than chess and there is only limited data of lower quality available compared to AlphaGo.
Random Sum-Product Forests with Residual Links
Tractable yet expressive density estimators are a key building block of probabilistic machine learning.
Padé Activation Units: End-to-end Learning of Flexible Activation Functions in Deep Networks
The performance of deep network learning strongly depends on the choice of the non-linear activation function associated with each neuron.
Declarative Learning-Based Programming as an Interface to AI Systems
Data-driven approaches are becoming more common as problem-solving techniques in many areas of research and industry.
Neural-Symbolic Argumentation Mining: an Argument in Favor of Deep Learning and Reasoning
Deep learning is bringing remarkable contributions to the field of argumentation mining, but the existing approaches still need to fill the gap toward performing advanced reasoning tasks.
Conditional Sum-Product Networks: Imposing Structure on Deep Probabilistic Architectures
In contrast, deep probabilistic models such as sum-product networks (SPNs) capture joint distributions in a tractable fashion, but still lack the expressive power of intractable models based on deep neural networks.
Was ist eine Professur fuer Kuenstliche Intelligenz?
The Federal Government of Germany aims to boost the research in the field of Artificial Intelligence (AI).
Propagation kernels: efficient graph kernels from propagated information
We introduce propagation kernels, a general graph-kernel framework for efficiently measuring the similarity of structured data.
Ranked #8 on
Graph Classification
on NCI109
SPFlow: An Easy and Extensible Library for Deep Probabilistic Learning using Sum-Product Networks
We introduce SPFlow, an open-source Python library providing a simple interface to inference, learning and manipulation routines for deep and tractable probabilistic models called Sum-Product Networks (SPNs).
Model-based Approximate Query Processing
However, classical AQP approaches suffer from various problems that limit the applicability to support the ad-hoc exploration of a new data set: (1) Classical AQP approaches that perform online sampling can support ad-hoc exploration queries but yield low quality if executed over rare subpopulations.
Structure Learning for Relational Logistic Regression: An Ensemble Approach
We consider the problem of learning Relational Logistic Regression (RLR).
Automatic Bayesian Density Analysis
Classical approaches for {exploratory data analysis} are usually not flexible enough to deal with the uncertainty inherent to real-world data: they are often restricted to fixed latent interaction models and homogeneous likelihoods; they are sensitive to missing, corrupt and anomalous data; moreover, their expressiveness generally comes at the price of intractable inference.
Probabilistic Deep Learning using Random Sum-Product Networks
The need for consistent treatment of uncertainty has recently triggered increased interest in probabilistic deep learning methods.
"Why Should I Trust Interactive Learners?" Explaining Interactive Queries of Classifiers to Users
Although interactive learning puts the user into the loop, the learner remains mostly a black box for the user.
Neural Conditional Gradients
The move from hand-designed to learned optimizers in machine learning has been quite successful for gradient-based and -free optimizers.
Lifted Filtering via Exchangeable Decomposition
We present a model for exact recursive Bayesian filtering based on lifted multiset states.
Coresets for Dependency Networks
Many applications infer the structure of a probabilistic graphical model from data to elucidate the relationships between variables.
Sum-Product Networks for Hybrid Domains
While all kinds of mixed data -from personal data, over panel and scientific data, to public and commercial data- are collected and stored, building probabilistic graphical models for these hybrid domains becomes more difficult.
Global Weisfeiler-Lehman Graph Kernels
Specifically, we introduce a novel graph kernel based on the $k$-dimensional Weisfeiler-Lehman algorithm.
A Unifying View of Explicit and Implicit Feature Maps of Graph Kernels
On this basis we propose exact and approximative feature maps for widely used graph kernels based on the kernel trick.
Faster Kernels for Graphs with Continuous Attributes via Hashing
While state-of-the-art kernels for graphs with discrete labels scale well to graphs with thousands of nodes, the few existing kernels for graphs with continuous attributes, unfortunately, do not scale well.
Machine Learning meets Data-Driven Journalism: Boosting International Understanding and Transparency in News Coverage
Migration crisis, climate change or tax havens: Global challenges need global solutions.
Lifted Convex Quadratic Programming
Symmetry is the essential element of lifted inference that has recently demon- strated the possibility to perform very efficient inference in highly-connected, but symmetric probabilistic models models.
How is a data-driven approach better than random choice in label space division for multi-label classification?
We show that fastgreedy and walktrap community detection methods on weighted label co-occurence graphs are 85-92% more likely to yield better F1 scores than random partitioning.
The Symbolic Interior Point Method
A recent trend in probabilistic inference emphasizes the codification of models in a formal syntax, with suitable high-level features such as individuals, relations, and connectives, enabling descriptive clarity, succinctness and circumventing the need for the modeler to engineer a custom solver.
Propagation Kernels
We introduce propagation kernels, a general graph-kernel framework for efficiently measuring the similarity of structured data.
Relational Linear Programs
A relational linear program (RLP) is a declarative LP template defining the objective and the constraints through the logical concepts of objects, relations, and quantified variables.
Mind the Nuisance: Gaussian Process Classification using Privileged Noise
That is, in contrast to the standard GPC setting, the latent function is not just a nuisance but a feature: it becomes a natural measure of confidence about the training data by modulating the slope of the GPC sigmoid likelihood function.
Efficient Information Theoretic Clustering on Discrete Lattices
We consider the problem of clustering data that reside on discrete, low dimensional lattices.
Dimension Reduction via Colour Refinement
We demonstrate empirically that colour refinement can indeed greatly reduce the cost of solving linear programs.
Symbolic Dynamic Programming for Continuous State and Observation POMDPs
In recent years, point- based value iteration methods have proven to be extremely effective techniques for finding (approximately) optimal dynamic programming solutions to POMDPs when an initial set of belief states is known.
Bayesian Logic Programs
Theyare a probabilistic extension of propositional logic and, hence, inherit some of the limitations of propositional logic, such as the difficulties to represent objects and relations.
