arXiv subjects

Yutong Xia

Publications and source records attributed to Yutong Xia.

22 records · Page 2Linked to original sources

arXiv2023

LargeST: A Benchmark Dataset for Large-Scale Traffic Forecasting

Road traffic forecasting plays a critical role in smart city initiatives and has experienced significant advancements thanks to the power of deep learning in capturing non-linear patterns of traffic data. However, the promising results achieved on current public datasets may not be applicable to practical scenarios due to limitations within these datasets. First, the limited sizes of them may not reflect the real-world scale of traffic networks. Second, the temporal coverage of these datasets is typically short, posing hurdles in studying long-term patterns and acquiring sufficient samples for training deep models. Third, these datasets often lack adequate metadata for sensors, which compromises the reliability and interpretability of the data. To mitigate these limitations, we introduce the LargeST benchmark dataset. It encompasses a total number of 8,600 sensors in California with a 5-year time coverage and includes comprehensive metadata. Using LargeST, we perform in-depth data analysis to extract data insights, benchmark well-known baselines in terms of their performance and efficiency, and identify challenges as well as opportunities for future research. We release the datasets and baseline implementations at: https://github.com/liuxu77/LargeST.

cs.LG↗

arXiv2023

Deciphering Spatio-Temporal Graph Forecasting: A Causal Lens and Treatment

Spatio-Temporal Graph (STG) forecasting is a fundamental task in many real-world applications. Spatio-Temporal Graph Neural Networks have emerged as the most popular method for STG forecasting, but they often struggle with temporal out-of-distribution (OoD) issues and dynamic spatial causation. In this paper, we propose a novel framework called CaST to tackle these two challenges via causal treatments. Concretely, leveraging a causal lens, we first build a structural causal model to decipher the data generation process of STGs. To handle the temporal OoD issue, we employ the back-door adjustment by a novel disentanglement block to separate invariant parts and temporal environments from input data. Moreover, we utilize the front-door adjustment and adopt the Hodge-Laplacian operator for edge-level convolution to model the ripple effect of causation. Experiments results on three real-world datasets demonstrate the effectiveness and practicality of CaST, which consistently outperforms existing methods with good interpretability.

cs.LG↗

arXiv2023

A note on additive complements of the squares

Let $\mathcal{S}=\{1^2,2^2,3^2,...\}$ be the set of squares and $\mathcal{W}=\{w_n\}_{n=1}^{\infty} \subset \mathbb{N}$ be an additive complement of $\mathcal{S}$ so that $\mathcal{S} + \mathcal{W} \supset \{n \in \mathbb{N}: n \geq N_0\}$ for some $N_0$. Let $\mathcal{R}_{\mathcal{S},\mathcal{W}}(n) = \#\{(s,w):n=s+w, s\in \mathcal{S}, w\in \mathcal{W}\} $. In 2017, Chen-Fang \cite{C-F} studied the lower bound of $\sum_{n=1}^NR_{\mathcal{S},\mathcal{W}}(n)$. In this note, we improve Cheng-Fang's result and get that $$\sum_{n=1}^NR_{\mathcal{S},\mathcal{W}}(n)-N\gg N^{1/2}.$$ As an application, we make some progress on a problem of Ben Green problem by showing that $$\limsup_{n\rightarrow\infty}\frac{\frac{π^2}{16}n^2-w_n}{n}\ge \fracπ{4}+\frac{0.193π^2}{8}.$$

math.NT↗

arXiv2022

AirFormer: Predicting Nationwide Air Quality in China with Transformers

Air pollution is a crucial issue affecting human health and livelihoods, as well as one of the barriers to economic and social growth. Forecasting air quality has become an increasingly important endeavor with significant social impacts, especially in emerging countries like China. In this paper, we present a novel Transformer architecture termed AirFormer to collectively predict nationwide air quality in China, with an unprecedented fine spatial granularity covering thousands of locations. AirFormer decouples the learning process into two stages -- 1) a bottom-up deterministic stage that contains two new types of self-attention mechanisms to efficiently learn spatio-temporal representations; 2) a top-down stochastic stage with latent variables to capture the intrinsic uncertainty of air quality data. We evaluate AirFormer with 4-year data from 1,085 stations in the Chinese Mainland. Compared to the state-of-the-art model, AirFormer reduces prediction errors by 5%~8% on 72-hour future predictions. Our source code is available at https://github.com/yoshall/airformer.

eess.SP↗