Unlocking the Potential of Transformers in Time Series Forecasting with Sharpness-Aware Minimization and Channel-Wise Attention

Transformer-based architectures achieved breakthrough performance in natural language processing and computer vision, yet they remain inferior to simpler linear baselines in multivariate long-term forecasting. To better understand this phenomenon, we start by studying a toy linear forecasting problem for which we show that transformers are incapable of converging to their true solution despite their high expressive power. We further identify the attention of transformers as being responsible for this low generalization capacity. Building upon this insight, we propose a shallow lightweight transformer model that successfully escapes bad local minima when optimized with sharpness-aware optimization. We empirically demonstrate that this result extends to all commonly used real-world multivariate time series datasets. In particular, SAMformer surpasses the current state-of-the-art model TSMixer by 14.33% on average, while having ~4 times fewer parameters. The code is available at https://github.com/romilbert/samformer.

Breaking Boundaries: Balancing Performance and Robustness in Deep Wireless Traffic Forecasting

Balancing the trade-off between accuracy and robustness is a long-standing challenge in time series forecasting. While most of existing robust algorithms have achieved certain suboptimal performance on clean data, sustaining the same performance level in the presence of data perturbations remains extremely hard. In this paper, we study a wide array of perturbation scenarios and propose novel defense mechanisms against adversarial attacks using real-world telecom data. We compare our strategy against two existing adversarial training algorithms under a range of maximal allowed perturbations, defined using $\ell_{\infty}$-norm, $\in [0.1,0.4]$. Our findings reveal that our hybrid strategy, which is composed of a classifier to detect adversarial examples, a denoiser to eliminate noise from the perturbed data samples, and a standard forecaster, achieves the best performance on both clean and perturbed data. Our optimal model can retain up to $92.02\%$ the performance of the original forecasting model in terms of Mean Squared Error (MSE) on clean data, while being more robust than the standard adversarially trained models on perturbed data. Its MSE is 2.71$\times$ and 2.51$\times$ lower than those of comparing methods on normal and perturbed data, respectively. In addition, the components of our models can be trained in parallel, resulting in better computational efficiency. Our results indicate that we can optimally balance the trade-off between the performance and robustness of forecasting models by improving the classifier and denoiser, even in the presence of sophisticated and destructive poisoning attacks.

A Hierarchical Transformer Encoder to Improve Entire Neoplasm Segmentation on Whole Slide Image of Hepatocellular Carcinoma

In digital histopathology, entire neoplasm segmentation on Whole Slide Image (WSI) of Hepatocellular Carcinoma (HCC) plays an important role, especially as a preprocessing filter to automatically exclude healthy tissue, in histological molecular correlations mining and other downstream histopathological tasks. The segmentation task remains challenging due to HCC's inherent high-heterogeneity and the lack of dependency learning in large field of view. In this article, we propose a novel deep learning architecture with a hierarchical Transformer encoder, HiTrans, to learn the global dependencies within expanded 4096$\times$4096 WSI patches. HiTrans is designed to encode and decode the patches with larger reception fields and the learned global dependencies, compared to the state-of-the-art Fully Convolutional Neural networks (FCNN). Empirical evaluations verified that HiTrans leads to better segmentation performance by taking into account regional and global dependency information.

A Critical Re-evaluation of Benchmark Datasets for (Deep) Learning-Based Matching Algorithms

Entity resolution (ER) is the process of identifying records that refer to the same entities within one or across multiple databases. Numerous techniques have been developed to tackle ER challenges over the years, with recent emphasis placed on machine and deep learning methods for the matching phase. However, the quality of the benchmark datasets typically used in the experimental evaluations of learning-based matching algorithms has not been examined in the literature. To cover this gap, we propose four different approaches to assessing the difficulty and appropriateness of 13 established datasets: two theoretical approaches, which involve new measures of linearity and existing measures of complexity, and two practical approaches: the difference between the best non-linear and linear matchers, as well as the difference between the best learning-based matcher and the perfect oracle. Our analysis demonstrates that most of the popular datasets pose rather easy classification tasks. As a result, they are not suitable for properly evaluating learning-based matching algorithms. To address this issue, we propose a new methodology for yielding benchmark datasets. We put it into practice by creating four new matching tasks, and we verify that these new benchmarks are more challenging and therefore more suitable for further advancements in the field.

Appliance Detection Using Very Low-Frequency Smart Meter Time Series

In recent years, smart meters have been widely adopted by electricity suppliers to improve the management of the smart grid system. These meters usually collect energy consumption data at a very low frequency (every 30min), enabling utilities to bill customers more accurately. To provide more personalized recommendations, the next step is to detect the appliances owned by customers, which is a challenging problem, due to the very-low meter reading frequency. Even though the appliance detection problem can be cast as a time series classification problem, with many such classifiers having been proposed in the literature, no study has applied and compared them on this specific problem. This paper presents an in-depth evaluation and comparison of state-of-the-art time series classifiers applied to detecting the presence/absence of diverse appliances in very low-frequency smart meter data. We report results with five real datasets. We first study the impact of the detection quality of 13 different appliances using 30min sampled data, and we subsequently propose an analysis of the possible detection performance gain by using a higher meter reading frequency. The results indicate that the performance of current time series classifiers varies significantly. Some of them, namely deep learning-based classifiers, provide promising results in terms of accuracy (especially for certain appliances), even using 30min sampled data, and are scalable to the large smart meter time series collections of energy consumption data currently available to electricity suppliers. Nevertheless, our study shows that more work is needed in this area to further improve the accuracy of the proposed solutions. This paper appeared in ACM e-Energy 2023.

Series2Graph: Graph-based Subsequence Anomaly Detection for Time Series

Subsequence anomaly detection in long sequences is an important problem with applications in a wide range of domains. However, the approaches proposed so far in the literature have severe limitations: they either require prior domain knowledge used to design the anomaly discovery algorithms, or become cumbersome and expensive to use in situations with recurrent anomalies of the same type. In this work, we address these problems, and propose an unsupervised method suitable for domain agnostic subsequence anomaly detection. Our method, Series2Graph, is based on a graph representation of a novel low-dimensionality embedding of subsequences. Series2Graph needs neither labeled instances (like supervised techniques) nor anomaly-free data (like zero-positive learning techniques), and identifies anomalies of varying lengths. The experimental results, on the largest set of synthetic and real datasets used to date, demonstrate that the proposed approach correctly identifies single and recurrent anomalies without any prior knowledge of their characteristics, outperforming by a large margin several competing approaches in accuracy, while being up to orders of magnitude faster. This paper has appeared in VLDB 2020.

dCAM: Dimension-wise Class Activation Map for Explaining Multivariate Data Series Classification

Data series classification is an important and challenging problem in data science. Explaining the classification decisions by finding the discriminant parts of the input that led the algorithm to some decisions is a real need in many applications. Convolutional neural networks perform well for the data series classification task; though, the explanations provided by this type of algorithm are poor for the specific case of multivariate data series. Addressing this important limitation is a significant challenge. In this paper, we propose a novel method that solves this problem by highlighting both the temporal and dimensional discriminant information. Our contribution is two-fold: we first describe a convolutional architecture that enables the comparison of dimensions; then, we propose a method that returns dCAM, a Dimension-wise Class Activation Map specifically designed for multivariate time series (and CNN-based models). Experiments with several synthetic and real datasets demonstrate that dCAM is not only more accurate than previous approaches, but the only viable solution for discriminant feature discovery and classification explanation in multivariate time series. This paper has appeared in SIGMOD'22.

SentiQ: A Probabilistic Logic Approach to Enhance Sentiment Analysis Tool Quality

The opinion expressed in various Web sites and social-media is an essential contributor to the decision making process of several organizations. Existing sentiment analysis tools aim to extract the polarity (i.e., positive, negative, neutral) from these opinionated contents. Despite the advance of the research in the field, sentiment analysis tools give \textit{inconsistent} polarities, which is harmful to business decisions. In this paper, we propose SentiQ, an unsupervised Markov logic Network-based approach that injects the semantic dimension in the tools through rules. It allows to detect and solve inconsistencies and then improves the overall accuracy of the tools. Preliminary experimental results demonstrate the usefulness of SentiQ.