Time series forecasting is crucial and challenging in the real world. The recent surge in interest regarding time series foundation models, which cater to a diverse array of downstream tasks, is noteworthy. However, existing methods often overlook the multi-scale nature of time series, an aspect crucial for precise forecasting. To bridge this gap, we propose HiMTM, a hierarchical multi-scale masked time series modeling method designed for long-term forecasting. Specifically, it comprises four integral components: (1) hierarchical multi-scale transformer (HMT) to capture temporal information at different scales; (2) decoupled encoder-decoder (DED) forces the encoder to focus on feature extraction, while the decoder to focus on pretext tasks; (3) multi-scale masked reconstruction (MMR) provides multi-stage supervision signals for pre-training; (4) cross-scale attention fine-tuning (CSA-FT) to capture dependencies between different scales for forecasting. Collectively, these components enhance multi-scale feature extraction capabilities in masked time series modeling and contribute to improved prediction accuracy. We conduct extensive experiments on 7 mainstream datasets to prove that HiMTM has obvious advantages over contemporary self-supervised and end-to-end learning methods. The effectiveness of HiMTM is further showcased by its application in the industry of natural gas demand forecasting.
As LLMs have become capable of processing more complex types of inputs, researchers have recently studied how to efficiently and affordably process possibly arbitrarily long sequences. One effective approach is to use a FIFO memory to store keys and values of an attention sublayer from past chunks to allow subsequent queries to attend. However, this approach requires a large memory and/or takes into the consideration the specific LM architecture. Moreover, due to the causal nature between the key-values in prior context and the queries at present, this approach cannot be extended to bidirectional attention such as in an encoder-decoder or PrefixLM decoder-only architecture. In this paper, we propose to use eviction policies, such as LRA and LFA, to reduce the memory size and adapt to various architectures, and we also propose the Attendre layer, a wait-to-attend mechanism by retrieving the key-value memory (K/V memory) with evicted queries in the query memory (Q memory). As a first step, we evaluate this method in the context length extension setup using the TriviaQA reading comprehension task, and show the effectiveness of the approach.
Graph clustering algorithms with autoencoder structures have recently gained popularity due to their efficient performance and low training cost. However, for existing graph autoencoder clustering algorithms based on GCN or GAT, not only do they lack good generalization ability, but also the number of clusters clustered by such autoencoder models is difficult to determine automatically. To solve this problem, we propose a new framework called Graph Clustering with Masked Autoencoders (GCMA). It employs our designed fusion autoencoder based on the graph masking method for the fusion coding of graph. It introduces our improved density-based clustering algorithm as a second decoder while decoding with multi-target reconstruction. By decoding the mask embedding, our model can capture more generalized and comprehensive knowledge. The number of clusters and clustering results can be output end-to-end while improving the generalization ability. As a nonparametric class method, extensive experiments demonstrate the superiority of \textit{GCMA} over state-of-the-art baselines.
U-Nets are a go-to, state-of-the-art neural architecture across numerous tasks for continuous signals on a square such as images and Partial Differential Equations (PDE), however their design and architecture is understudied. In this paper, we provide a framework for designing and analysing general U-Net architectures. We present theoretical results which characterise the role of the encoder and decoder in a U-Net, their high-resolution scaling limits and their conjugacy to ResNets via preconditioning. We propose Multi-ResNets, U-Nets with a simplified, wavelet-based encoder without learnable parameters. Further, we show how to design novel U-Net architectures which encode function constraints, natural bases, or the geometry of the data. In diffusion models, our framework enables us to identify that high-frequency information is dominated by noise exponentially faster, and show how U-Nets with average pooling exploit this. In our experiments, we demonstrate how Multi-ResNets achieve competitive and often superior performance compared to classical U-Nets in image segmentation, PDE surrogate modelling, and generative modelling with diffusion models. Our U-Net framework paves the way to study the theoretical properties of U-Nets and design natural, scalable neural architectures for a multitude of problems beyond the square.
One of the most important challenges in text generation systems is to produce outputs that are not only correct but also diverse. Recently, Minimum Bayes-Risk (MBR) decoding has gained prominence for generating sentences of the highest quality among the decoding algorithms. However, existing algorithms proposed for generating diverse outputs are predominantly based on beam search or random sampling, thus their output quality is capped by these underlying methods. In this paper, we investigate an alternative approach -- we develop diversity-promoting decoding algorithms by enforcing diversity objectives to MBR decoding. We propose two variants of MBR, Diverse MBR (DMBR) and $k$-medoids MBR (KMBR), methods to generate a set of sentences with high quality and diversity. We evaluate DMBR and KMBR on a variety of directed text generation tasks using encoder-decoder models and a large language model with prompting. The experimental results show that the proposed method achieves a better trade-off than the diverse beam search and sampling algorithms.
This paper develops a graph reinforcement learning approach to online planning of the schedule and destinations of electric aircraft that comprise an urban air mobility (UAM) fleet operating across multiple vertiports. This fleet scheduling problem is formulated to consider time-varying demand, constraints related to vertiport capacity, aircraft capacity and airspace safety guidelines, uncertainties related to take-off delay, weather-induced route closures, and unanticipated aircraft downtime. Collectively, such a formulation presents greater complexity, and potentially increased realism, than in existing UAM fleet planning implementations. To address these complexities, a new policy architecture is constructed, primary components of which include: graph capsule conv-nets for encoding vertiport and aircraft-fleet states both abstracted as graphs; transformer layers encoding time series information on demand and passenger fare; and a Multi-head Attention-based decoder that uses the encoded information to compute the probability of selecting each available destination for an aircraft. Trained with Proximal Policy Optimization, this policy architecture shows significantly better performance in terms of daily averaged profits on unseen test scenarios involving 8 vertiports and 40 aircraft, when compared to a random baseline and genetic algorithm-derived optimal solutions, while being nearly 1000 times faster in execution than the latter.
The problem of audio-to-audio (A2A) style transfer involves replacing the style features of the source audio with those from the target audio while preserving the content related attributes of the source audio. In this paper, we propose an efficient approach, termed as Zero-shot Emotion Style Transfer (ZEST), that allows the transfer of emotional content present in the given source audio with the one embedded in the target audio while retaining the speaker and speech content from the source. The proposed system builds upon decomposing speech into semantic tokens, speaker representations and emotion embeddings. Using these factors, we propose a framework to reconstruct the pitch contour of the given speech signal and train a decoder that reconstructs the speech signal. The model is trained using a self-supervision based reconstruction loss. During conversion, the emotion embedding is alone derived from the target audio, while rest of the factors are derived from the source audio. In our experiments, we show that, even without using parallel training data or labels from the source or target audio, we illustrate zero shot emotion transfer capabilities of the proposed ZEST model using objective and subjective quality evaluations.
Omnidirectional stereo matching (OSM) is an essential and reliable means for $360^{\circ}$ depth sensing. However, following earlier works on conventional stereo matching, prior state-of-the-art (SOTA) methods rely on a 3D encoder-decoder block to regularize the cost volume, causing the whole system complicated and sub-optimal results. Recently, the Recurrent All-pairs Field Transforms (RAFT) based approach employs the recurrent update in 2D and has efficiently improved image-matching tasks, ie, optical flow, and stereo matching. To bridge the gap between OSM and RAFT, we mainly propose an opposite adaptive weighting scheme to seamlessly transform the outputs of spherical sweeping of OSM into the required inputs for the recurrent update, thus creating a recurrent omnidirectional stereo matching (RomniStereo) algorithm. Furthermore, we introduce two techniques, ie, grid embedding and adaptive context feature generation, which also contribute to RomniStereo's performance. Our best model improves the average MAE metric by 40.7\% over the previous SOTA baseline across five datasets. When visualizing the results, our models demonstrate clear advantages on both synthetic and realistic examples. The code is available at \url{https://github.com/HalleyJiang/RomniStereo}.
End-to-end multi-talker speech recognition has garnered great interest as an effective approach to directly transcribe overlapped speech from multiple speakers. Current methods typically adopt either 1) single-input multiple-output (SIMO) models with a branched encoder, or 2) single-input single-output (SISO) models based on attention-based encoder-decoder architecture with serialized output training (SOT). In this work, we propose a Cross-Speaker Encoding (CSE) network to address the limitations of SIMO models by aggregating cross-speaker representations. Furthermore, the CSE model is integrated with SOT to leverage both the advantages of SIMO and SISO while mitigating their drawbacks. To the best of our knowledge, this work represents an early effort to integrate SIMO and SISO for multi-talker speech recognition. Experiments on the two-speaker LibrispeechMix dataset show that the CES model reduces word error rate (WER) by 8% over the SIMO baseline. The CSE-SOT model reduces WER by 10% overall and by 16% on high-overlap speech compared to the SOT model. Code is available at https://github.com/kjw11/CSEnet-ASR.
Diffusion models are the current state of the art for generating photorealistic images. Controlling the sampling process for constrained image generation tasks such as inpainting, however, remains challenging since exact conditioning on such constraints is intractable. While existing methods use various techniques to approximate the constrained posterior, this paper proposes to exploit the ability of Tractable Probabilistic Models (TPMs) to exactly and efficiently compute the constrained posterior, and to leverage this signal to steer the denoising process of diffusion models. Specifically, this paper adopts a class of expressive TPMs termed Probabilistic Circuits (PCs). Building upon prior advances, we further scale up PCs and make them capable of guiding the image generation process of diffusion models. Empirical results suggest that our approach can consistently improve the overall quality and semantic coherence of inpainted images across three natural image datasets (i.e., CelebA-HQ, ImageNet, and LSUN) with only $\sim\! 10 \%$ additional computational overhead brought by the TPM. Further, with the help of an image encoder and decoder, our method can readily accept semantic constraints on specific regions of the image, which opens up the potential for more controlled image generation tasks. In addition to proposing a new framework for constrained image generation, this paper highlights the benefit of more tractable models and motivates the development of expressive TPMs.
Low-density parity-check (LDPC) codes have been successfully commercialized in communication systems due to their strong error correction capabilities and simple decoding process. However, the error-floor phenomenon of LDPC codes, in which the error rate stops decreasing rapidly at a certain level, presents challenges for achieving extremely low error rates and deploying LDPC codes in scenarios demanding ultra-high reliability. In this work, we propose training methods for neural min-sum (NMS) decoders to eliminate the error-floor effect. First, by leveraging the boosting learning technique of ensemble networks, we divide the decoding network into two neural decoders and train the post decoder to be specialized for uncorrected words that the first decoder fails to correct. Secondly, to address the vanishing gradient issue in training, we introduce a block-wise training schedule that locally trains a block of weights while retraining the preceding block. Lastly, we show that assigning different weights to unsatisfied check nodes effectively lowers the error-floor with a minimal number of weights. By applying these training methods to standard LDPC codes, we achieve the best error-floor performance compared to other decoding methods. The proposed NMS decoder, optimized solely through novel training methods without additional modules, can be integrated into existing LDPC decoders without incurring extra hardware costs. The source code is available at https://github.com/ghy1228/LDPC_Error_Floor .
To resolve the semantic ambiguity in texts, we propose a model, which innovatively combines a knowledge graph with an improved attention mechanism. An existing knowledge base is utilized to enrich the text with relevant contextual concepts. The model operates at both character and word levels to deepen its understanding by integrating the concepts. We first adopt information gain to select import words. Then an encoder-decoder framework is used to encode the text along with the related concepts. The local attention mechanism adjusts the weight of each concept, reducing the influence of irrelevant or noisy concepts during classification. We improve the calculation formula for attention scores in the local self-attention mechanism, ensuring that words with different frequencies of occurrence in the text receive higher attention scores. Finally, the model employs a Bi-directional Gated Recurrent Unit (Bi-GRU), which is effective in feature extraction from texts for improved classification accuracy. Its performance is demonstrated on datasets such as AGNews, Ohsumed, and TagMyNews, achieving accuracy of 75.1%, 58.7%, and 68.5% respectively, showing its effectiveness in classifying tasks.
Speech separation involves extracting an individual speaker's voice from a multi-speaker audio signal. The increasing complexity of real-world environments, where multiple speakers might converse simultaneously, underscores the importance of effective speech separation techniques. This work presents a single-microphone speaker separation network with TF attention aiming at noisy and reverberant environments. We dub this new architecture as Separation TF Attention Network (Sep-TFAnet). In addition, we present a variant of the separation network, dubbed $ \text{Sep-TFAnet}^{\text{VAD}}$, which incorporates a voice activity detector (VAD) into the separation network. The separation module is based on a temporal convolutional network (TCN) backbone inspired by the Conv-Tasnet architecture with multiple modifications. Rather than a learned encoder and decoder, we use short-time Fourier transform (STFT) and inverse short-time Fourier transform (iSTFT) for the analysis and synthesis, respectively. Our system is specially developed for human-robotic interactions and should support online mode. The separation capabilities of $ \text{Sep-TFAnet}^{\text{VAD}}$ and Sep-TFAnet were evaluated and extensively analyzed under several acoustic conditions, demonstrating their advantages over competing methods. Since separation networks trained on simulated data tend to perform poorly on real recordings, we also demonstrate the ability of the proposed scheme to better generalize to realistic examples recorded in our acoustic lab by a humanoid robot. Project page: https://Sep-TFAnet.github.io
Recent work showed the possibility of building open-vocabulary large language models (LLMs) that directly operate on pixel representations. These models are implemented as autoencoders that reconstruct masked patches of rendered text. However, these pixel-based LLMs are limited to discriminative tasks (e.g., classification) and, similar to BERT, cannot be used to generate text. Therefore, they cannot be used for generative tasks such as free-form question answering. In this work, we introduce PIXAR, the first pixel-based autoregressive LLM that performs text generation. Consisting of only a decoder, PIXAR can perform free-form generative tasks while keeping the number of parameters on par with previous encoder-decoder models. Furthermore, we highlight the challenges of generating text as non-noisy images and show this is due to using a maximum likelihood objective. To overcome this problem, we propose an adversarial pretraining stage that improves the readability and accuracy of PIXAR by 8.1 on LAMBADA and 8.5 on bAbI -- making it comparable to GPT-2 on text generation tasks. This paves the way to build open-vocabulary LLMs that operate on perceptual input only and calls into question the necessity of the usual symbolic input representation, i.e., text as (sub)tokens.
Database systems often rely on historical query traces to perform workload-based performance tuning. However, real production workloads are time-evolving, making historical queries ineffective for optimizing future workloads. To address this challenge, we propose SIBYL, an end-to-end machine learning-based framework that accurately forecasts a sequence of future queries, with the entire query statements, in various prediction windows. Drawing insights from real-workloads, we propose template-based featurization techniques and develop a stacked-LSTM with an encoder-decoder architecture for accurate forecasting of query workloads. We also develop techniques to improve forecasting accuracy over large prediction windows and achieve high scalability over large workloads with high variability in arrival rates of queries. Finally, we propose techniques to handle workload drifts. Our evaluation on four real workloads demonstrates that SIBYL can forecast workloads with an $87.3\%$ median F1 score, and can result in $1.7\times$ and $1.3\times$ performance improvement when applied to materialized view selection and index selection applications, respectively.
Large language models (LLMs) have made significant advancements in code-related tasks, yet many LLMs treat code as simple sequences, neglecting its structured nature. We introduce AST-T5, a novel pretraining paradigm that leverages the Abstract Syntax Tree (AST) for enhanced code generation, transpilation, and understanding. Using dynamic programming, our AST-Aware Segmentation retains code structure, while our AST-Aware Span Corruption objective equips the model to reconstruct various code structures. Unlike other models, AST-T5 avoids intricate program analyses or architectural changes, so it integrates seamlessly with any encoder-decoder Transformer. Evaluations show that AST-T5 consistently outperforms similar-sized LMs across various code-related tasks. Structure-awareness makes AST-T5 particularly powerful in code-to-code tasks, surpassing CodeT5 by 2 points in exact match score for the Bugs2Fix task and by 3 points in exact match score for Java-C# Transpilation in CodeXGLUE. Our code and model are publicly available at https://github.com/gonglinyuan/ast_t5.
We present WidthFormer, a novel transformer-based module to compute Bird's-Eye-View (BEV) representations from multi-view cameras for real-time autonomous-driving applications. WidthFormer is computationally efficient, robust and does not require any special engineering effort to deploy. We first introduce a novel 3D positional encoding mechanism capable of accurately encapsulating 3D geometric information, which enables our model to compute high-quality BEV representations with only a single transformer decoder layer. This mechanism is also beneficial for existing sparse 3D object detectors. Inspired by the recently proposed works, we further improve our model's efficiency by vertically compressing the image features when serving as attention keys and values, and then we develop two modules to compensate for potential information loss due to feature compression. Experimental evaluation on the widely-used nuScenes 3D object detection benchmark demonstrates that our method outperforms previous approaches across different 3D detection architectures. More importantly, our model is highly efficient. For example, when using $256\times 704$ input images, it achieves 1.5 ms and 2.8 ms latency on NVIDIA 3090 GPU and Horizon Journey-5 computation solutions. Furthermore, WidthFormer also exhibits strong robustness to different degrees of camera perturbations. Our study offers valuable insights into the deployment of BEV transformation methods in real-world, complex road environments. Code is available at https://github.com/ChenhongyiYang/WidthFormer .
High-quality imaging is crucial for ensuring safety supervision and intelligent deployment in fields like transportation and industry. It enables precise and detailed monitoring of operations, facilitating timely detection of potential hazards and efficient management. However, adverse weather conditions, such as atmospheric haziness and precipitation, can have a significant impact on image quality. When the atmosphere contains dense haze or water droplets, the incident light scatters, leading to degraded captured images. This degradation is evident in the form of image blur and reduced contrast, increasing the likelihood of incorrect assessments and interpretations by intelligent imaging systems (IIS). To address the challenge of restoring degraded images in hazy and rainy conditions, this paper proposes a novel multi-view knowledge-guided scene recovery network (termed MvKSR). Specifically, guided filtering is performed on the degraded image to separate high/low-frequency components. Subsequently, an en-decoder-based multi-view feature coarse extraction module (MCE) is used to coarsely extract features from different views of the degraded image. The multi-view feature fine fusion module (MFF) will learn and infer the restoration of degraded images through mixed supervision under different views. Additionally, we suggest an atrous residual block to handle global restoration and local repair in hazy/rainy/mixed scenes. Extensive experimental results demonstrate that MvKSR outperforms other state-of-the-art methods in terms of efficiency and stability for restoring degraded scenarios in IIS.
Accurate per-object distance estimation is crucial in safety-critical applications such as autonomous driving, surveillance, and robotics. Existing approaches rely on two scales: local information (i.e., the bounding box proportions) or global information, which encodes the semantics of the scene as well as the spatial relations with neighboring objects. However, these approaches may struggle with long-range objects and in the presence of strong occlusions or unusual visual patterns. In this respect, our work aims to strengthen both local and global cues. Our architecture -- named DistFormer -- builds upon three major components acting jointly: i) a robust context encoder extracting fine-grained per-object representations; ii) a masked encoder-decoder module exploiting self-supervision to promote the learning of useful per-object features; iii) a global refinement module that aggregates object representations and computes a joint, spatially-consistent estimation. To evaluate the effectiveness of DistFormer, we conduct experiments on the standard KITTI dataset and the large-scale NuScenes and MOTSynth datasets. Such datasets cover various indoor/outdoor environments, changing weather conditions, appearances, and camera viewpoints. Our comprehensive analysis shows that DistFormer outperforms existing methods. Moreover, we further delve into its generalization capabilities, showing its regularization benefits in zero-shot synth-to-real transfer.
We present an end-to-end transformer-based framework named TRDLU for the task of Document Layout Understanding (DLU). DLU is the fundamental task to automatically understand document structures. To accurately detect content boxes and classify them into semantically meaningful classes from various formats of documents is still an open challenge. Recently, transformer-based detection neural networks have shown their capability over traditional convolutional-based methods in the object detection area. In this paper, we consider DLU as a detection task, and introduce TRDLU which integrates transformer-based vision backbone and transformer encoder-decoder as detection pipeline. TRDLU is only a visual feature-based framework, but its performance is even better than multi-modal feature-based models. To the best of our knowledge, this is the first study of employing a fully transformer-based framework in DLU tasks. We evaluated TRDLU on three different DLU benchmark datasets, each with strong baselines. TRDLU outperforms the current state-of-the-art methods on all of them.