United States

Recently, there has been a surge of Transformer-based solutions for the long-term time series forecasting (LTSF) task. Despite the growing performance over the past few years, \emph{we question the validity of this line of research in this work}. Specifically, Transformers is arguably the most successful solution to extract the semantic correlations among the elements in a long sequence. However, in time series modeling, we are to extract the temporal relations in \emph{an ordered set of continuous points}. While employing positional encoding and using tokens to embed sub-series in Transformers facilitate preserving some ordering information, the nature of the \emph{permutation-invariant} self-attention mechanism inevitably results in temporal information loss. 
To validate our claim, we introduce a set of embarrassingly simple one-layer linear models named \emph{LTSF-Linear} for comparison. Experimental results on nine real-life datasets show that \emph{LTSF-Linear} surprisingly outperforms existing sophisticated Transformer-based LTSF models in all cases, and often by a large margin. Moreover, we conduct comprehensive empirical studies to explore the impacts of various design elements of LTSF models on their temporal relation extraction capability. We hope this surprising finding opens up new research directions for the LTSF task. We also advocate revisiting the validity of Transformer-based solutions for other time series analysis tasks (e.g., anomaly detection) in the future.

AAAI 2023

Are Transformers Effective for Time Series Forecasting?

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-23 is the Thirty-Seventh AAAI Conference on Artificial Intelligence. The theme of this conference is to create collaborative bridges within and beyond AI. Like previous AAAI conferences, AAAI-23 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and two new activities: a Bridge Program and a Lab Program. Many of these activities are tailored to the theme of bridges and all are selected according to the highest standards, with additional programs for students and young researchers. 
AAAI is providing you with a conference planner, which you can use to help organize your itinerary of activities. This includes talks to attend in person, talks to attend remotely, breaks with colleagues and your site seeing activities. To access this conference planner, please go to [https://aaai-2023.takemobi.io](https://aaai-2023.takemobi.io).

In order to access this site, you need to register. If you haven't already, please register [here](https://aaai.org/Conferences/AAAI-23/registration/).


The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines.

poster

Current 3D single object tracking methods are typically based on VoteNet, a 3D region proposal network. Despite the success, using a single seed point feature as the cue for offset learning in VoteNet prevents high-quality 3D proposals from being generated. Moreover, seed points with different importance are treated equally in the voting process, aggravating this defect. To address these issues, we propose a novel global-local transformer voting scheme to provide more informative cues and guide the model pay more attention on potential seed points, promoting the generation of high-quality 3D proposals. Technically, a global-local transformer (GLT) module is employed to integrate object- and patch-aware prior into seed point features to effectively form strong feature representation for geometric positions of the seed points, thus providing more robust and accurate cues for offset learning. Subsequently, a simple yet effective training strategy is designed to train the GLT module. We develop an importance prediction branch to learn the potential importance of the seed points and treat the output weights vector as a training constraint term. By incorporating the above components together, we exhibit a superior tracking method GLT-T. Extensive experiments on challenging KITTI and NuScenes benchmarks demonstrate that GLT-T achieves state-of-the-art performance in the 3D single object tracking task. Besides, further ablation studies show the advantages of the proposed global-local transformer voting scheme over the original VoteNet. The source code and models will be released.

GLT-T: Global-Local Transformer Voting for 3D Single Object Tracking in Point Clouds

As text generated by large language models proliferates, it becomes vital to understand how humans engage with such text, and whether or not they are able to detect when the text they are reading did not originate with a human writer.
Prior work on human detection of generated text focuses on the case where an entire passage is either human-written or machine-generated. In this paper, we study a more realistic setting where text begins as human-written and transitions to being generated by state-of-the-art neural language models. We show that, while annotators often struggle at this task, there is substantial variance in annotator skill and that given proper incentives, annotators can improve at this task over time. Furthermore, we conduct a detailed comparison study and analyze how a variety of variables (model size, decoding strategy, fine-tuning, prompt genre, etc.) affect human detection performance. Finally, we collect error annotations from our participants and use them to show that certain textual genres influence models to make different types of errors and that certain sentence-level features correlate highly with annotator selection. We release the RoFT dataset: a collection of over 21,000 human annotations paired with error classifications to encourage future work in human detection and evaluation of generated text.

Real or Fake Text?: Investigating Human Ability to Detect Boundaries Between Human-Written and Machine-Generated Text

Utilizing amortized variational inference for latent-action reinforcement learning (RL) has been shown to be an effective approach in Task-oriented Dialogue (ToD) systems for optimizing dialogue success.Until now, categorical posteriors have been argued to be one of the main drivers of performance. In this work we revisit Gaussian variational posteriors for latent-action RL and show that they can yield even better performance than categoricals. We achieve this by introducing an improved variational inference objective for learning continuous representations without auxiliary learning objectives, which streamlines the training procedure. Moreover, we propose ways to regularize the latent dialogue policy, which helps to retain good response coherence. Using continuous latent representations our model achieves state of the art dialogue success rate on the MultiWOZ benchmark, and also compares well to categorical latent methods in response coherence.

Taming Continuous Posteriors for Latent Variational Dialogue Policies

The ensemble attack with average weights can be leveraged for increasing the transferability of universal adversarial perturbation (UAP) by training with multiple Convolutional Neural Networks (CNNs). However, after analyzing the Pearson Correlation Coefficients (PCCs) between the ensemble logits and individual logits of the crafted UAP trained by the ensemble attack, we find that one CNN plays a dominant role during the optimization. 
Consequently, this average weighted strategy will weaken the contributions of other CNNs and thus limit the transferability for other black-box CNNs. To deal with this bias issue, the primary attempt is to leverage the Kullback–Leibler (KL) divergence loss to encourage the joint contribution from different CNNs, which is still insufficient. After decoupling the KL loss into a target-class part and a non-target-class part, the main issue lies in that the non-target knowledge will be significantly suppressed due to the increasing logit of the target class. 
In this study, we simply adopt a KL loss that only considers the non-target classes for addressing the dominant bias issue. Besides, to further boost the transferability, we incorporate the min-max learning framework to self-adjust the ensemble weights for each CNN.Experiments results validate that considering the non-target KL loss can achieve superior transferability than the original KL loss by a large margin, and the min-max training can provide a mutual benefit in adversarial ensemble attacks.  The source code is available at: https://github.com/WJJLL/ND-MM.

Exploring Non-Target Knowledge for Improving Ensemble Universal Adversarial Attacks

Attention modules, which adaptively weight and refine features according to the importance of the input, have become a critical technique to boost the capability of convolutional neural networks. However, most existing attention modules are heuristic without a sound interpretation, and thus, require empirical engineering to design structure and operators within the modules. To handle the above issue, based on our 'less is more important' observation, we propose an Attention Module guided by Probability Density Function (PDF), dubbed PdfAM, which enjoys a rational motivation and requires few empirical structure designs. Concretely, we observe that pixels with less occurrence are prone to be textural details or foreground objects with much importance to aid vision tasks. Thus, with PDF values adopted as a smooth and anti-noise alternative to the pixel occurrence frequency, we design our PdfAM by first estimating the PDF based on some distribution assumption, and then predicting a 3D attention map via applying a negative correlation between the attention weights and the estimated PDF values. Furthermore, we develop learnable PDF-rescale parameters so as to adaptively transform the estimated PDF and predict a customized negative correlation. Experiments show that our PdfAM consistently boosts various networks under both high- and low-level vision tasks, and also performs favorably against other attention modules in terms of accuracy and convergence.

Less Is More Important: An Attention Module Guided by Probability Density Function for Convolutional Neural Networks

Point cloud completion, as the upstream procedure of 3D recognition and segmentation, has become an essential part of many tasks such as navigation and scene understanding. While various point cloud completion models have demonstrated their powerful capabilities, their robustness against adversarial attacks, which have been proven to be fatally malicious towards deep neural networks, remains unknown. In addition, existing attack approaches towards point cloud classifiers cannot be applied to the completion models due to different output forms and attack purposes.
In order to evaluate the robustness of the completion models, we propose PointCA, the first adversarial attack against 3D point cloud completion models. PointCA can generate adversarial point clouds that maintain high similarity with the original ones, while being completed as another object with totally different semantic information. Specifically, by jointly exploring the adversarial point clouds in the geometry space and the feature space, we develop a gradient-based algorithm to construct perturbative point data such that the representation discrepancy can be minimized between the adversarial example and the target point set. Furthermore, to launch a stealthier attack, we innovatively employ the neighbourhood density information to tailor the perturbation constraint, leading to geometry-aware and distribution-adaptive modifications for each point.
Extensive experiments against different premier point cloud completion networks show that PointCA can cause the performance degradation from 77.9% to 16.7%, with the structure chamfer distance kept  below 0.01. We conclude that existing completion models are severely vulnerable to adversarial examples, and state-of-the-art defenses for point cloud classification will be partially invalid when applied to incomplete and uneven point cloud data. 

PointCA: Evaluating the Robustness of 3D Point Cloud Completion Models against Adversarial Examples

The click-through rate (CTR) prediction task is to predict whether a user will click on the recommended item. As mind-boggling amounts of data are produced online daily, accelerating CTR prediction model training is critical to ensuring an up-to-date model and reducing the training cost. One approach to increase the training speed is to apply large batch training. However, as shown in computer vision and natural language processing tasks, training with a large batch easily suffers from the loss of accuracy. Our experiments show that previous scaling rules fail in the training of CTR prediction neural networks. To tackle this problem, we first theoretically show that different frequencies of ids make it challenging to scale hyperparameters when scaling the batch size. To stabilize the training process in a large batch size setting, we develop the adaptive Column-wise Clipping (CowClip). It enables an easy and effective scaling rule for the embeddings, which keeps the learning rate unchanged and scales the L2 loss. We conduct extensive experiments with four CTR prediction networks on two real-world datasets and successfully scaled 128 times the original batch size without accuracy loss. In particular, for CTR prediction model DeepFM training on the Criteo dataset, our optimization framework enlarges the batch size from 1K to 128K with over 0.1% AUC improvement and reduces training time from 12 hours to 10 minutes on a single V100 GPU. Our code locates at github.com/bytedance/LargeBatchCTR.

CowClip: Reducing CTR Prediction Model Training Time from 12 hours to 10 minutes on 1 GPU

To estimate item frequencies of data streams with limited space, sketches are widely used in real applications, including real-time web analytics, network monitoring, and self-driving. Sketches can be viewed as a model which maps the identifier of a stream item to the corresponding frequency domain. Starting from the premise, we envision a neural data structure, which we term the meta-sketch, to go beyond the basic structure of conventional sketches. The meta-sketch learns basic sketching abilities from meta-tasks constituted with synthetic datasets following Zipf distributions in the pre-training phase, and can be fast adapted to real (skewed) distributions in the adaption phase. Extensive experiments demonstrate the performance gains of the meta-sketch and offer insights into our proposals.

Meta-sketch: A Neural Data Structure for Estimating Item Frequencies of Data Streams

We explore a fairness-related challenge that arises in generative models. The challenge is that biased training data with imbalanced demographics may yield a high asymmetry in size of generated samples across distinct groups. We focus on practically-relevant scenarios wherein demographic labels are not available and therefore the design of a fair generative model is non-straightforward. In this paper, we propose an optimization framework that regulates the unfairness under such practical settings via one statistical measure, LeCam (LC)-divergence. Specifically to quantify the degree of unfairness, we employ a balanced-yet-small reference dataset and then measure its distance with generated samples using the LC-divergence, which is shown to be particularly instrumental to a \emph{small} size of the reference dataset. We take a variational optimization approach to implement the LC-based measure. Experiments on benchmark real datasets demonstrate that the proposed framework can significantly improve the fairness performance while maintaining realistic sample quality for a wide range of the reference set size all the way down to 1% relative to training set.

A Fair Generative Model Using LeCam Divergence

Humans and other living beings have the ability of short and long-term memorization during their entire lifespan. However, most existing Continual Learning (CL) methods can only account for short-term information when training on infinite streams of data. In this paper, we develop a new unsupervised continual learning framework consisting of two memory systems using Variational Autoencoders (VAEs). We develop a Short-Term Memory (STM), and a parameterised scalable memory implemented by a Teacher model aiming to preserve the long-term information. To incrementally enrich the Teacher's knowledge during training, we propose the Knowledge Incremental Assimilation Mechanism (KIAM), which evaluates the knowledge similarity between the STM and the already accumulated information as signals to expand the Teacher's capacity. Then we train a VAE as a Student module and propose a new Knowledge Distillation (KD) approach that gradually transfers generative knowledge from the Teacher to the Student module. To ensure the quality and diversity of knowledge in KD, we propose a new expert pruning approach that selectively removes the Teacher's redundant parameters, associated with certain unnecessary experts that have preserved the knowledge corresponding to overlapping probabilistic representations. This mechanism further reduces the complexity of the Teacher's module while ensuring the diversity of knowledge for the KD procedure. We show theoretically and empirically that the proposed framework can train a statistically diversified Teacher module for continual VAE learning which is applicable to infinite data streams.

Premium content

Are Transformers Effective for Time Series Forecasting?

Downloads

Next from AAAI 2023

GLT-T: Global-Local Transformer Voting for 3D Single Object Tracking in Point Clouds

Similar lecture

Learning Adversarially Robust Sparse Networks via Weight Reparameterization

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES