arXiv subjects

Shengrui Wang

Publications and source records attributed to Shengrui Wang.

30 records · Page 2Linked to original sources

arXiv2024

Kolmogorov-Arnold Networks for Time Series: Bridging Predictive Power and Interpretability

Kolmogorov-Arnold Networks (KAN) is a groundbreaking model recently proposed by the MIT team, representing a revolutionary approach with the potential to be a game-changer in the field. This innovative concept has rapidly garnered worldwide interest within the AI community. Inspired by the Kolmogorov-Arnold representation theorem, KAN utilizes spline-parametrized univariate functions in place of traditional linear weights, enabling them to dynamically learn activation patterns and significantly enhancing interpretability. In this paper, we explore the application of KAN to time series forecasting and propose two variants: T-KAN and MT-KAN. T-KAN is designed to detect concept drift within time series and can explain the nonlinear relationships between predictions and previous time steps through symbolic regression, making it highly interpretable in dynamically changing environments. MT-KAN, on the other hand, improves predictive performance by effectively uncovering and leveraging the complex relationships among variables in multivariate time series. Experiments validate the effectiveness of these approaches, demonstrating that T-KAN and MT-KAN significantly outperform traditional methods in time series forecasting tasks, not only enhancing predictive accuracy but also improving model interpretability. This research opens new avenues for adaptive forecasting models, highlighting the potential of KAN as a powerful and interpretable tool in predictive analytics.

cs.LG↗

arXiv2024

DRNet: A Decision-Making Method for Autonomous Lane Changingwith Deep Reinforcement Learning

Machine learning techniques have outperformed numerous rule-based methods for decision-making in autonomous vehicles. Despite recent efforts, lane changing remains a major challenge, due to the complex driving scenarios and changeable social behaviors of surrounding vehicles. To help improve the state of the art, we propose to leveraging the emerging \underline{D}eep \underline{R}einforcement learning (DRL) approach for la\underline{NE} changing at the \underline{T}actical level. To this end, we present "DRNet", a novel and highly efficient DRL-based framework that enables a DRL agent to learn to drive by executing reasonable lane changing on simulated highways with an arbitrary number of lanes, and considering driving style of surrounding vehicles to make better decisions. Furthermore, to achieve a safe policy for decision-making, DRNet incorporates ideas from safety verification, the most important component of autonomous driving, to ensure that only safe actions are chosen at any time. The setting of our state representation and reward function enables the trained agent to take appropriate actions in a real-world-like simulator. Our DRL agent has the ability to learn the desired task without causing collisions and outperforms DDQN and other baseline models.

cs.RO↗

arXiv2023

Successive Data Injection in Conditional Quantum GAN Applied to Time Series Anomaly Detection

Classical GAN architectures have shown interesting results for solving anomaly detection problems in general and for time series anomalies in particular, such as those arising in communication networks. In recent years, several quantum GAN architectures have been proposed in the literature. When detecting anomalies in time series using QGANs, huge challenges arise due to the limited number of qubits compared to the size of the data. To address these challenges, we propose a new high-dimensional encoding approach, named Successive Data Injection (SuDaI). In this approach, we explore a larger portion of the quantum state than that in the conventional angle encoding, the method used predominantly in the literature, through repeated data injections into the quantum state. SuDaI encoding allows us to adapt the QGAN for anomaly detection with network data of a much higher dimensionality than with the existing known QGANs implementations. In addition, SuDaI encoding applies to other types of high-dimensional time series and can be used in contexts beyond anomaly detection and QGANs, opening up therefore multiple fields of application.

cs.LG↗

arXiv2023

Characterizing Financial Market Coverage using Artificial Intelligence

This paper scrutinizes a database of over 4900 YouTube videos to characterize financial market coverage. Financial market coverage generates a large number of videos. Therefore, watching these videos to derive actionable insights could be challenging and complex. In this paper, we leverage Whisper, a speech-to-text model from OpenAI, to generate a text corpus of market coverage videos from Bloomberg and Yahoo Finance. We employ natural language processing to extract insights regarding language use from the market coverage. Moreover, we examine the prominent presence of trending topics and their evolution over time, and the impacts that some individuals and organizations have on the financial market. Our characterization highlights the dynamics of the financial market coverage and provides valuable insights reflecting broad discussions regarding recent financial events and the world economy.

q-fin.ST↗

arXiv2022

Modeling Regime Shifts in Multiple Time Series

We investigate the problem of discovering and modeling regime shifts in an ecosystem comprising multiple time series known as co-evolving time series. Regime shifts refer to the changing behaviors exhibited by series at different time intervals. Learning these changing behaviors is a key step toward time series forecasting. While advances have been made, existing methods suffer from one or more of the following shortcomings: (1) failure to take relationships between time series into consideration for discovering regimes in multiple time series; (2) lack of an effective approach that models time-dependent behaviors exhibited by series; (3) difficulties in handling data discontinuities which may be informative. Most of the existing methods are unable to handle all of these three issues in a unified framework. This, therefore, motivates our effort to devise a principled approach for modeling interactions and time-dependency in co-evolving time series. Specifically, we model an ecosystem of multiple time series by summarizing the heavy ensemble of time series into a lighter and more meaningful structure called a \textit{mapping grid}. By using the mapping grid, our model first learns time series behavioral dependencies through a dynamic network representation, then learns the regime transition mechanism via a full time-dependent Cox regression model. The originality of our approach lies in modeling interactions between time series in regime identification and in modeling time-dependent regime transition probabilities, usually assumed to be static in existing work.

cs.LG↗

arXiv2022

Discovering Affinity Relationships between Personality Types

Psychology research findings suggest that personality is related to differences in friendship characteristics and that some personality traits correlate with linguistic behavior. In this paper, we investigate the influence that personality may have on affinity formation. To this end, we derive affinity relationships from social media interactions, examine personality based on language use to discover the emotional stability of affinity relationships, and measure semantic similarity at the personality type level to understand the logic behind the development of affinity. Specifically, we conduct extensive experiments using a publicly available dataset containing information on individuals who self-identified with a Myers-Briggs personality type. Our results identify certain influential personality types that weigh more heavily on affinity relationships and show that personality can be predicted from spontaneous language with an F-1 score superior to 0.76. Future research avenues are proposed.

cs.SI↗

arXiv2022

Neural forecasting at scale

We study the problem of efficiently scaling ensemble-based deep neural networks for multi-step time series (TS) forecasting on a large set of time series. Current state-of-the-art deep ensemble models have high memory and computational requirements, hampering their use to forecast millions of TS in practical scenarios. We propose N-BEATS(P), a global parallel variant of the N-BEATS model designed to allow simultaneous training of multiple univariate TS forecasting models. Our model addresses the practical limitations of related models, reducing the training time by half and memory requirement by a factor of 5, while keeping the same level of accuracy in all TS forecasting settings. We have performed multiple experiments detailing the various ways to train our model and have obtained results that demonstrate its capacity to generalize in various forecasting conditions and setups.

cs.LG↗

arXiv2021

COVID-19: Detecting Depression Signals during Stay-At-Home Period

The new coronavirus outbreak has been officially declared a global pandemic by the World Health Organization. To grapple with the rapid spread of this ongoing pandemic, most countries have banned indoor and outdoor gatherings and ordered their residents to stay home. Given the developing situation with coronavirus, mental health is an important challenge in our society today. In this paper, we discuss the investigation of social media postings to detect signals relevant to depression. To this end, we utilize topic modeling features and a collection of psycholinguistic and mental-well-being attributes to develop statistical models to characterize and facilitate representation of the more subtle aspects of depression. Furthermore, we predict whether signals relevant to depression are likely to grow significantly as time moves forward. Our best classifier yields F-1 scores as high as 0.8 and surpasses the utilized baseline by a considerable margin, 0.173. In closing, we propose several future research avenues.

cs.SI↗

arXiv2021

Investigating Moral Foundations from Web Trending Topics

Moral foundations theory helps understand differences in morality across cultures. In this paper, we propose a model to predict moral foundations (MF) from social media trending topics. We also investigate whether differences in MF influence emotional traits. Our results are promising and leave room for future research avenues.

cs.SI↗

arXiv2020

Spatiotemporal Adaptive Neural Network for Long-term Forecasting of Financial Time Series

Optimal decision-making in social settings is often based on forecasts from time series (TS) data. Recently, several approaches using deep neural networks (DNNs) such as recurrent neural networks (RNNs) have been introduced for TS forecasting and have shown promising results. However, the applicability of these approaches is being questioned for TS settings where there is a lack of quality training data and where the TS to forecast exhibit complex behaviors. Examples of such settings include financial TS forecasting, where producing accurate and consistent long-term forecasts is notoriously difficult. In this work, we investigate whether DNN-based models can be used to forecast these TS conjointly by learning a joint representation of the series instead of computing the forecast from the raw time-series representations. To this end, we make use of the dynamic factor graph (DFG) to build a multivariate autoregressive model. We investigate a common limitation of RNNs that rely on the DFG framework and propose a novel variable-length attention-based mechanism (ACTM) to address it. With ACTM, it is possible to vary the autoregressive order of a TS model over time and model a larger set of probability distributions than with previous approaches. Using this mechanism, we propose a self-supervised DNN architecture for multivariate TS forecasting that learns and takes advantage of the relationships between them. We test our model on two datasets covering 19 years of investment fund activities. Our experimental results show that the proposed approach significantly outperforms typical DNN-based and statistical models at forecasting the 21-day price trajectory. We point out how improving forecasting accuracy and knowing which forecaster to use can improve the excess return of autonomous trading strategies.

cs.LG↗

arXiv2019

A Comparative Study of Different Approaches for Tracking Communities in Evolving Social Networks

In real-world social networks, there is an increasing interest in tracking the evolution of groups of users and detecting the various changes they are liable to undergo. Several approaches have been proposed for this. In studying these approaches, we observed that most of them use a two-stage process. In the first stage, they run an algorithm to identify groups of users at each timestamp. In the second stage, a pair-wise comparison based on a similarity measure is employed to track groups of users and detect changes they may undergo. While the majority of existing approaches use a two-stage process, they all run different algorithms to identify communities and rely on different similarity measures to track groups of users over time. Noting that the different approaches may perform differently depending on the dynamic social network under investigation, we decided to make a high level survey of some existing tracking approaches and then do a comparative analysis of some of them. In our analysis, we compared the algorithms in two main situations: $(1)$ when groups of users do not overlap and $(2)$ when the groups are overlapping. The study was done on three different testbeds extracted from the DBLP, Autonomous System (AS) and Yelp datasets.

cs.SI↗

arXiv2012

Deep-sequencing of the Peach Latent Mosaic Viroid Reveals New Aspects of Population Heterogeneity

Viroids are small circular single-stranded infectious RNAs that are characterized by a relatively high mutation level. Knowledge of their sequence heterogeneity remains largely elusive, and, as yet, no strategy attempting to address this question from a population dynamics point of view is in place. In order to address these important questions, a GF305 indicator peach tree was infected with a single variant of the Avsunviroidae family member Peach latent mosaic viroid (PLMVd). Six months post-inoculation, full-length circular conformers of PLMVd were isolated, deep-sequenced and the resulting sequences analyzed using an original bioinformatics scheme specifically designed and developed in order to evaluate the richness of a given the sequence's population. Two distinct libraries were analyzed, and yielded 1125 and 1061 different PLMVd variants respectively, making this study the most productive to date (by more than an order of magnitude) in terms of the reporting of novel viroid sequences. Sequence variants exhibiting up to ~20% of mutations relative to the inoculated viroid were retrieved, clearly illustrating the high divergence dynamic inside a unique population. Using a novel hierarchical clustering algorithm, the different variants obtained were grouped into either 7 or 8 clusters depending on the library being analyzed. Most of the sequences contained, on average, between 4.6 and 6.3 mutations relative to the variant used initially to inoculate the plant. Interestingly, it was possible to reconstitute the sequence evolution between these clusters. On top of providing a reliable pipeline for the treatment of viroid deep-sequencing, this study sheds new light on the importance of the sequence variation that may take place in a viroid population and which may result in the formation of a quasi-species.

q-bio.PE↗