arXiv subjects

Lars Schmidt-Thieme

Publications and source records attributed to Lars Schmidt-Thieme.

At least 73 records · Page 4Linked to original sources

arXiv2022

Attention, Filling in The Gaps for Generalization in Routing Problems

Machine Learning (ML) methods have become a useful tool for tackling vehicle routing problems, either in combination with popular heuristics or as standalone models. However, current methods suffer from poor generalization when tackling problems of different sizes or different distributions. As a result, ML in vehicle routing has witnessed an expansion phase with new methodologies being created for particular problem instances that become infeasible at larger problem sizes. This paper aims at encouraging the consolidation of the field through understanding and improving current existing models, namely the attention model by Kool et al. We identify two discrepancy categories for VRP generalization. The first is based on the differences that are inherent to the problems themselves, and the second relates to architectural weaknesses that limit the model's ability to generalize. Our contribution becomes threefold: We first target model discrepancies by adapting the Kool et al. method and its loss function for Sparse Dynamic Attention based on the alpha-entmax activation. We then target inherent differences through the use of a mixed instance training method that has been shown to outperform single instance training in certain scenarios. Finally, we introduce a framework for inference level data augmentation that improves performance by leveraging the model's lack of invariance to rotation and dilation changes.

cs.LG↗

arXiv2022

Learning to Control Local Search for Combinatorial Optimization

Combinatorial optimization problems are encountered in many practical contexts such as logistics and production, but exact solutions are particularly difficult to find and usually NP-hard for considerable problem sizes. To compute approximate solutions, a zoo of generic as well as problem-specific variants of local search is commonly used. However, which variant to apply to which particular problem is difficult to decide even for experts. In this paper we identify three independent algorithmic aspects of such local search algorithms and formalize their sequential selection over an optimization process as Markov Decision Process (MDP). We design a deep graph neural network as policy model for this MDP, yielding a learned controller for local search called NeuroLS. Ample experimental evidence shows that NeuroLS is able to outperform both, well-known general purpose local search controllers from Operations Research as well as latest machine learning-based approaches.

cs.LG↗

arXiv2022

Zero-Shot AutoML with Pretrained Models

Given a new dataset D and a low compute budget, how should we choose a pre-trained model to fine-tune to D, and set the fine-tuning hyperparameters without risking overfitting, particularly if D is small? Here, we extend automated machine learning (AutoML) to best make these choices. Our domain-independent meta-learning approach learns a zero-shot surrogate model which, at test time, allows to select the right deep learning (DL) pipeline (including the pre-trained model and fine-tuning hyperparameters) for a new dataset D given only trivial meta-features describing D such as image resolution or the number of classes. To train this zero-shot model, we collect performance data for many DL pipelines on a large collection of datasets and meta-train on this data to minimize a pairwise ranking objective. We evaluate our approach under the strict time limit of the vision track of the ChaLearn AutoDL challenge benchmark, clearly outperforming all challenge contenders.

cs.LG↗

arXiv2022

Large Neighborhood Search based on Neural Construction Heuristics

We propose a Large Neighborhood Search (LNS) approach utilizing a learned construction heuristic based on neural networks as repair operator to solve the vehicle routing problem with time windows (VRPTW). Our method uses graph neural networks to encode the problem and auto-regressively decodes a solution and is trained with reinforcement learning on the construction task without requiring any labels for supervision. The neural repair operator is combined with a local search routine, heuristic destruction operators and a selection procedure applied to a small population to arrive at a sophisticated solution approach. The key idea is to use the learned model to re-construct the partially destructed solution and to introduce randomness via the destruction heuristics (or the stochastic policy itself) to effectively explore a large neighborhood.

cs.LG↗

arXiv2022

End-to-End Image-Based Fashion Recommendation

In fashion-based recommendation settings, incorporating the item image features is considered a crucial factor, and it has shown significant improvements to many traditional models, including but not limited to matrix factorization, auto-encoders, and nearest neighbor models. While there are numerous image-based recommender approaches that utilize dedicated deep neural networks, comparisons to attribute-aware models are often disregarded despite their ability to be easily extended to leverage items' image features. In this paper, we propose a simple yet effective attribute-aware model that incorporates image features for better item representation learning in item recommendation tasks. The proposed model utilizes items' image features extracted by a calibrated ResNet50 component. We present an ablation study to compare incorporating the image features using three different techniques into the recommender system component that can seamlessly leverage any available items' attributes. Experiments on two image-based real-world recommender systems datasets show that the proposed model significantly outperforms all state-of-the-art image-based models.

cs.AI↗

arXiv2022

CARCA: Context and Attribute-Aware Next-Item Recommendation via Cross-Attention

In sparse recommender settings, users' context and item attributes play a crucial role in deciding which items to recommend next. Despite that, recent works in sequential and time-aware recommendations usually either ignore both aspects or only consider one of them, limiting their predictive performance. In this paper, we address these limitations by proposing a context and attribute-aware recommender model (CARCA) that can capture the dynamic nature of the user profiles in terms of contextual features and item attributes via dedicated multi-head self-attention blocks that extract profile-level features and predicting item scores. Also, unlike many of the current state-of-the-art sequential item recommendation approaches that use a simple dot-product between the most recent item's latent features and the target items embeddings for scoring, CARCA uses cross-attention between all profile items and the target items to predict their final scores. This cross-attention allows CARCA to harness the correlation between old and recent items in the user profile and their influence on deciding which item to recommend next. Experiments on four real-world recommender system datasets show that the proposed model significantly outperforms all state-of-the-art models in the task of item recommendation and achieving improvements of up to 53% in Normalized Discounted Cumulative Gain (NDCG) and Hit-Ratio. Results also show that CARCA outperformed several state-of-the-art dedicated image-based recommender systems by merely utilizing image attributes extracted from a pre-trained ResNet50 in a black-box fashion.

cs.IR↗

arXiv2022

Improving Amharic Handwritten Word Recognition Using Auxiliary Task

Amharic is one of the official languages of the Federal Democratic Republic of Ethiopia. It is one of the languages that use an Ethiopic script which is derived from Gee'z, ancient and currently a liturgical language. Amharic is also one of the most widely used literature-rich languages of Ethiopia. There are very limited innovative and customized research works in Amharic optical character recognition (OCR) in general and Amharic handwritten text recognition in particular. In this study, Amharic handwritten word recognition will be investigated. State-of-the-art deep learning techniques including convolutional neural networks together with recurrent neural networks and connectionist temporal classification (CTC) loss were used to make the recognition in an end-to-end fashion. More importantly, an innovative way of complementing the loss function using the auxiliary task from the row-wise similarities of the Amharic alphabet was tested to show a significant recognition improvement over a baseline method. Such findings will promote innovative problem-specific solutions as well as will open insight to a generalized solution that emerges from problem-specific domains.

cs.CV↗

arXiv2022

Positive-Unlabeled Domain Adaptation

Domain Adaptation methodologies have shown to effectively generalize from a labeled source domain to a label scarce target domain. Previous research has either focused on unlabeled domain adaptation without any target supervision or semi-supervised domain adaptation with few labeled target examples per class. On the other hand Positive-Unlabeled (PU-) Learning has attracted increasing interest in the weakly supervised learning literature since in quite some real world applications positive labels are much easier to obtain than negative ones. In this work we are the first to introduce the challenge of Positive-Unlabeled Domain Adaptation where we aim to generalise from a fully labeled source domain to a target domain where only positive and unlabeled data is available. We present a novel two-step learning approach to this problem by firstly identifying reliable positive and negative pseudo-labels in the target domain guided by source domain labels and a positive-unlabeled risk estimator. This enables us to use a standard classifier on the target domain in a second step. We validate our approach by running experiments on benchmark datasets for visual object recognition. Furthermore we propose real world examples for our setting and validate our superior performance on parking occupancy data.

cs.LG↗

arXiv2022

A.I. and Data-Driven Mobility at Volkswagen Financial Services AG

Machine learning is being widely adapted in industrial applications owing to the capabilities of commercially available hardware and rapidly advancing research. Volkswagen Financial Services (VWFS), as a market leader in vehicle leasing services, aims to leverage existing proprietary data and the latest research to enhance existing and derive new business processes. The collaboration between Information Systems and Machine Learning Lab (ISMLL) and VWFS serves to realize this goal. In this paper, we propose methods in the fields of recommender systems, object detection, and forecasting that enable data-driven decisions for the vehicle life-cycle at VWFS.

cs.AI↗

arXiv2022

Supervised Permutation Invariant Networks for Solving the CVRP with Bounded Fleet Size

Learning to solve combinatorial optimization problems, such as the vehicle routing problem, offers great computational advantages over classical operations research solvers and heuristics. The recently developed deep reinforcement learning approaches either improve an initially given solution iteratively or sequentially construct a set of individual tours. However, most of the existing learning-based approaches are not able to work for a fixed number of vehicles and thus bypass the complex assignment problem of the customers onto an apriori given number of available vehicles. On the other hand, this makes them less suitable for real applications, as many logistic service providers rely on solutions provided for a specific bounded fleet size and cannot accommodate short term changes to the number of vehicles. In contrast we propose a powerful supervised deep learning framework that constructs a complete tour plan from scratch while respecting an apriori fixed number of available vehicles. In combination with an efficient post-processing scheme, our supervised approach is not only much faster and easier to train but also achieves competitive results that incorporate the practical aspect of vehicle costs. In thorough controlled experiments we compare our method to multiple state-of-the-art approaches where we demonstrate stable performance, while utilizing less vehicles and shed some light on existent inconsistencies in the experimentation protocols of the related work.

cs.LG↗

arXiv2021

Multimodal Meta-Learning for Time Series Regression

Recent work has shown the efficiency of deep learning models such as Fully Convolutional Networks (FCN) or Recurrent Neural Networks (RNN) to deal with Time Series Regression (TSR) problems. These models sometimes need a lot of data to be able to generalize, yet the time series are sometimes not long enough to be able to learn patterns. Therefore, it is important to make use of information across time series to improve learning. In this paper, we will explore the idea of using meta-learning for quickly adapting model parameters to new short-history time series by modifying the original idea of Model Agnostic Meta-Learning (MAML) \cite{finn2017model}. Moreover, based on prior work on multimodal MAML \cite{vuorio2019multimodal}, we propose a method for conditioning parameters of the model through an auxiliary network that encodes global information of the time series to extract meta-features. Finally, we apply the data to time series of different domains, such as pollution measurements, heart-rate sensors, and electrical battery data. We show empirically that our proposed meta-learning method learns TSR with few data fast and outperforms the baselines in 9 of 12 experiments.

cs.LG↗

arXiv2021

Do We Really Need Deep Learning Models for Time Series Forecasting?

Time series forecasting is a crucial task in machine learning, as it has a wide range of applications including but not limited to forecasting electricity consumption, traffic, and air quality. Traditional forecasting models rely on rolling averages, vector auto-regression and auto-regressive integrated moving averages. On the other hand, deep learning and matrix factorization models have been recently proposed to tackle the same problem with more competitive performance. However, one major drawback of such models is that they tend to be overly complex in comparison to traditional techniques. In this paper, we report the results of prominent deep learning models with respect to a well-known machine learning baseline, a Gradient Boosting Regression Tree (GBRT) model. Similar to the deep neural network (DNN) models, we transform the time series forecasting task into a window-based regression problem. Furthermore, we feature-engineered the input and output structure of the GBRT model, such that, for each training window, the target values are concatenated with external features, and then flattened to form one input instance for a multi-output GBRT model. We conducted a comparative study on nine datasets for eight state-of-the-art deep-learning models that were presented at top-level conferences in the last years. The results demonstrate that the window-based input transformation boosts the performance of a simple GBRT model to levels that outperform all state-of-the-art DNN models evaluated in this paper.

cs.LG↗

arXiv2021

Improving Hyperparameter Optimization by Planning Ahead

Hyperparameter optimization (HPO) is generally treated as a bi-level optimization problem that involves fitting a (probabilistic) surrogate model to a set of observed hyperparameter responses, e.g. validation loss, and consequently maximizing an acquisition function using a surrogate model to identify good hyperparameter candidates for evaluation. The choice of a surrogate and/or acquisition function can be further improved via knowledge transfer across related tasks. In this paper, we propose a novel transfer learning approach, defined within the context of model-based reinforcement learning, where we represent the surrogate as an ensemble of probabilistic models that allows trajectory sampling. We further propose a new variant of model predictive control which employs a simple look-ahead strategy as a policy that optimizes a sequence of actions, representing hyperparameter candidates to expedite HPO. Our experiments on three meta-datasets comparing to state-of-the-art HPO algorithms including a model-free reinforcement learning approach show that the proposed method can outperform all baselines by exploiting a simple planning-based policy.

cs.LG↗

arXiv2021

Deep Metric Learning for Ground Images

Ground texture based localization methods are potential prospects for low-cost, high-accuracy self-localization solutions for robots. These methods estimate the pose of a given query image, i.e. the current observation of the ground from a downward-facing camera, in respect to a set of reference images whose poses are known in the application area. In this work, we deal with the initial localization task, in which we have no prior knowledge about the current robot positioning. In this situation, the localization method would have to consider all available reference images. However, in order to reduce computational effort and the risk of receiving a wrong result, we would like to consider only those reference images that are actually overlapping with the query image. For this purpose, we propose a deep metric learning approach that retrieves the most similar reference images to the query image. In contrast to existing approaches to image retrieval for ground images, our approach achieves significantly better recall performance and improves the localization performance of a state-of-the-art ground texture based localization method.

cs.CV↗

arXiv2021

Multi-script Handwritten Digit Recognition Using Multi-task Learning

Handwritten digit recognition is one of the extensively studied area in machine learning. Apart from the wider research on handwritten digit recognition on MNIST dataset, there are many other research works on various script recognition. However, it is not very common for multi-script digit recognition which encourage the development of robust and multipurpose systems. Additionally working on multi-script digit recognition enables multi-task learning, considering the script classification as a related task for instance. It is evident that multi-task learning improves model performance through inductive transfer using the information contained in related tasks. Therefore, in this study multi-script handwritten digit recognition using multi-task learning will be investigated. As a specific case of demonstrating the solution to the problem, Amharic handwritten character recognition will also be experimented. The handwritten digits of three scripts including Latin, Arabic and Kannada are studied to show that multi-task models with reformulation of the individual tasks have shown promising results. In this study a novel way of using the individual tasks predictions was proposed to help classification performance and regularize the different loss for the purpose of the main task. This finding has outperformed the baseline and the conventional multi-task learning models. More importantly, it avoided the need for weighting the different losses of the tasks, which is one of the challenges in multi-task learning.

cs.CV↗

arXiv2021

RP-DQN: An application of Q-Learning to Vehicle Routing Problems

In this paper we present a new approach to tackle complex routing problems with an improved state representation that utilizes the model complexity better than previous methods. We enable this by training from temporal differences. Specifically Q-Learning is employed. We show that our approach achieves state-of-the-art performance for autoregressive policies that sequentially insert nodes to construct solutions on the CVRP. Additionally, we are the first to tackle the MDVRP with machine learning methods and demonstrate that this problem type greatly benefits from our approach over other ML methods.

cs.LG↗

arXiv2021

Hyperparameter Optimization with Differentiable Metafeatures

Metafeatures, or dataset characteristics, have been shown to improve the performance of hyperparameter optimization (HPO). Conventionally, metafeatures are precomputed and used to measure the similarity between datasets, leading to a better initialization of HPO models. In this paper, we propose a cross dataset surrogate model called Differentiable Metafeature-based Surrogate (DMFBS), that predicts the hyperparameter response, i.e. validation loss, of a model trained on the dataset at hand. In contrast to existing models, DMFBS i) integrates a differentiable metafeature extractor and ii) is optimized using a novel multi-task loss, linking manifold regularization with a dataset similarity measure learned via an auxiliary dataset identification meta-task, effectively enforcing the response approximation for similar datasets to be similar. We compare DMFBS against several recent models for HPO on three large meta-datasets and show that it consistently outperforms all of them with an average 10% improvement. Finally, we provide an extensive ablation study that examines the different components of our approach.

cs.LG↗

arXiv2021

Dataset2Vec: Learning Dataset Meta-Features

Meta-learning, or learning to learn, is a machine learning approach that utilizes prior learning experiences to expedite the learning process on unseen tasks. As a data-driven approach, meta-learning requires meta-features that represent the primary learning tasks or datasets, and are estimated traditonally as engineered dataset statistics that require expert domain knowledge tailored for every meta-task. In this paper, first, we propose a meta-feature extractor called Dataset2Vec that combines the versatility of engineered dataset meta-features with the expressivity of meta-features learned by deep neural networks. Primary learning tasks or datasets are represented as hierarchical sets, i.e., as a set of sets, esp. as a set of predictor/target pairs, and then a DeepSet architecture is employed to regress meta-features on them. Second, we propose a novel auxiliary meta-learning task with abundant data called dataset similarity learning that aims to predict if two batches stem from the same dataset or different ones. In an experiment on a large-scale hyperparameter optimization task for 120 UCI datasets with varying schemas as a meta-learning task, we show that the meta-features of Dataset2Vec outperform the expert engineered meta-features and thus demonstrate the usefulness of learned meta-features for datasets with varying schemas for the first time.

cs.LG↗