arXiv subjects

Chen Zhu

Publications and source records attributed to Chen Zhu.

At least 109 records · Page 6Linked to original sources

arXiv2023

How Many Demonstrations Do You Need for In-context Learning?

Large language models (LLMs) are capable to perform complex reasoning by in-context learning (ICL) when provided with a few input-output demonstrations (demos) and more powerful when intermediate reasoning steps ("chain of thoughts (CoT)") of the demos are given. Is it necessary to use multi-demo in ICL? In this paper, we study ICL using fewer demos for each test query on the tasks in~\cite{wei2022chain}. Surprisingly, we do not observe significant degradation when using only one randomly chosen demo. To study this phenomenon, for each test query, we categorize demos into "correct demos" leading to the correct answer, and "wrong demos" resulting in wrong answers. Our analysis reveals an inherent bias in those widely studied datasets: most demos are correct for a majority of test queries, which explains the good performance of using one random demo. Moreover, ICL (with and w/o CoT) using only one correct demo significantly outperforms all-demo ICL adopted by most previous works, indicating the weakness of LLMs in finding correct demo(s) for input queries, which is difficult to evaluate on the biased datasets. Furthermore, we observe a counterintuitive behavior of ICL using multi-demo, i.e., its accuracy degrades(improves) when given more correct(wrong) demos. This implies that ICL can be easily misguided by interference among demos and their spurious correlations. Our analyses highlight several fundamental challenges that need to be addressed in LLMs training, ICL, and benchmark design.

cs.AI↗

arXiv2022

Multi-Level Association Rule Mining for Wireless Network Time Series Data

Key performance indicators(KPIs) are of great significance in the monitoring of wireless network service quality. The network service quality can be improved by adjusting relevant configuration parameters(CPs) of the base station. However, there are numerous CPs and different cells may affect each other, which bring great challenges to the association analysis of wireless network data. In this paper, we propose an adjustable multi-level association rule mining framework, which can quantitatively mine association rules at each level with environmental information, including engineering parameters and performance management(PMs), and it has interpretability at each level. Specifically, We first cluster similar cells, then quantify KPIs and CPs, and integrate expert knowledge into the association rule mining model, which improve the robustness of the model. The experimental results in real world dataset prove the effectiveness of our method.

cs.NI↗

arXiv2022

CPMLHO:Hyperparameter Tuning via Cutting Plane and Mixed-Level Optimization

The hyperparameter optimization of neural network can be expressed as a bilevel optimization problem. The bilevel optimization is used to automatically update the hyperparameter, and the gradient of the hyperparameter is the approximate gradient based on the best response function. Finding the best response function is very time consuming. In this paper we propose CPMLHO, a new hyperparameter optimization method using cutting plane method and mixed-level objective function.The cutting plane is added to the inner layer to constrain the space of the response function. To obtain more accurate hypergradient,the mixed-level can flexibly adjust the loss function by using the loss of the training set and the verification set. Compared to existing methods, the experimental results show that our method can automatically update the hyperparameters in the training process, and can find more superior hyperparameters with higher accuracy and faster convergence.

cs.LG↗

arXiv2022

Ferroelectricity induced by the absorption of water molecules on double helix SnIP

We study the ferroelectricity in a one-dimensional system composed of a double helix SnIP with absorbing water molecules. Our ab initio calculations reveal two factors that are critical to the electrical polarization. The first one is the orientation of polarized water molecules staying in the R2 region of SnIP. The second one is the displacement of I atom which roots from subtle interaction with absorbed water molecules. A reasonable scenario of polarization flipping is proposed in this study. In the scenario, the water molecule is rolling-up with keeping the magnitude of its electrical dipole and changing its direction, meanwhile, the displacement of I atoms is also reversed. Highly tunable polarization can be achieved by applying strain, with 26.5% of polarization enhancement by applying tensile strain, with only 4% degradation is observed with 4% compressive strain. Finally, the direct band gap is also found to be correlated with strain.

cond-mat.mtrl-sci↗

arXiv2022

Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors

Deep learning is increasingly moving towards a transfer learning paradigm whereby large foundation models are fine-tuned on downstream tasks, starting from an initialization learned on the source task. But an initialization contains relatively little information about the source task. Instead, we show that we can learn highly informative posteriors from the source task, through supervised or self-supervised approaches, which then serve as the basis for priors that modify the whole loss surface on the downstream task. This simple modular approach enables significant performance gains and more data-efficient learning on a variety of downstream classification and segmentation tasks, serving as a drop-in replacement for standard pre-training strategies. These highly informative priors also can be saved for future use, similar to pre-trained weights, and stand in contrast to the zero-mean isotropic uninformative priors that are typically used in Bayesian deep learning.

cs.LG↗

arXiv2022

Robust Optimization as Data Augmentation for Large-scale Graphs

Data augmentation helps neural networks generalize better by enlarging the training set, but it remains an open question how to effectively augment graph data to enhance the performance of GNNs (Graph Neural Networks). While most existing graph regularizers focus on manipulating graph topological structures by adding/removing edges, we offer a method to augment node features for better performance. We propose FLAG (Free Large-scale Adversarial Augmentation on Graphs), which iteratively augments node features with gradient-based adversarial perturbations during training. By making the model invariant to small fluctuations in input data, our method helps models generalize to out-of-distribution samples and boosts model performance at test time. FLAG is a general-purpose approach for graph data, which universally works in node classification, link prediction, and graph classification tasks. FLAG is also highly flexible and scalable, and is deployable with arbitrary GNN backbones and large-scale datasets. We demonstrate the efficacy and stability of our method through extensive experiments and ablation studies. We also provide intuitive observations for a deeper understanding of our method.

cs.LG↗

arXiv2022

Plug-In Inversion: Model-Agnostic Inversion for Vision with Data Augmentations

Existing techniques for model inversion typically rely on hard-to-tune regularizers, such as total variation or feature regularization, which must be individually calibrated for each network in order to produce adequate images. In this work, we introduce Plug-In Inversion, which relies on a simple set of augmentations and does not require excessive hyper-parameter tuning. Under our proposed augmentation-based scheme, the same set of augmentation hyper-parameters can be used for inverting a wide range of image classification models, regardless of input dimensions or the architecture. We illustrate the practicality of our approach by inverting Vision Transformers (ViTs) and Multi-Layer Perceptrons (MLPs) trained on the ImageNet dataset, tasks which to the best of our knowledge have not been successfully accomplished by any previous works.

cs.CV↗

arXiv2021

Complexity-Oriented Per-shot Video Coding Optimization

Current per-shot encoding schemes aim to improve the compression efficiency by shot-level optimization. It splits a source video sequence into shots and imposes optimal sets of encoding parameters to each shot. Per-shot encoding achieved approximately 20% bitrate savings over baseline fixed QP encoding at the expense of pre-processing complexity. However, the adjustable parameter space of the current per-shot encoding schemes only has spatial resolution and QP/CRF, resulting in a lack of encoding flexibility. In this paper, we extend the per-shot encoding framework in the complexity dimension. We believe that per-shot encoding with flexible complexity will help in deploying user-generated content. We propose a rate-distortion-complexity optimization process for encoders and a methodology to determine the coding parameters under the constraints of complexities and bitrate ladders. Experimental results show that our proposed method achieves complexity constraints ranging from 100% to 3% in a dense form compared to the slowest per-shot anchor. With similar complexities of the per-shot scheme fixed in specific presets, our proposed method achieves BDrate gain up to -19.17%.

eess.IV↗

arXiv2021

Long-Short Transformer: Efficient Transformers for Language and Vision

Transformers have achieved success in both language and vision domains. However, it is prohibitively expensive to scale them to long sequences such as long documents or high-resolution images, because self-attention mechanism has quadratic time and memory complexities with respect to the input sequence length. In this paper, we propose Long-Short Transformer (Transformer-LS), an efficient self-attention mechanism for modeling long sequences with linear complexity for both language and vision tasks. It aggregates a novel long-range attention with dynamic projection to model distant correlations and a short-term attention to capture fine-grained local correlations. We propose a dual normalization strategy to account for the scale mismatch between the two attention mechanisms. Transformer-LS can be applied to both autoregressive and bidirectional models without additional complexity. Our method outperforms the state-of-the-art models on multiple tasks in language and vision domains, including the Long Range Arena benchmark, autoregressive language modeling, and ImageNet classification. For instance, Transformer-LS achieves 0.97 test BPC on enwik8 using half the number of parameters than previous method, while being faster and is able to handle 3x as long sequences compared to its full-attention version on the same hardware. On ImageNet, it can obtain the state-of-the-art results (e.g., a moderate size of 55.8M model solely trained on 224x224 ImageNet-1K can obtain Top-1 accuracy 84.1%), while being more scalable on high-resolution images. The source code and models are released at https://github.com/NVIDIA/transformer-ls .

cs.CV↗

arXiv2021

GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training

Innovations in neural architectures have fostered significant breakthroughs in language modeling and computer vision. Unfortunately, novel architectures often result in challenging hyper-parameter choices and training instability if the network parameters are not properly initialized. A number of architecture-specific initialization schemes have been proposed, but these schemes are not always portable to new architectures. This paper presents GradInit, an automated and architecture agnostic method for initializing neural networks. GradInit is based on a simple heuristic; the norm of each network layer is adjusted so that a single step of SGD or Adam with prescribed hyperparameters results in the smallest possible loss value. This adjustment is done by introducing a scalar multiplier variable in front of each parameter block, and then optimizing these variables using a simple numerical scheme. GradInit accelerates the convergence and test performance of many convolutional architectures, both with or without skip connections, and even without normalization layers. It also improves the stability of the original Transformer architecture for machine translation, enabling training it without learning rate warmup using either Adam or SGD under a wide range of learning rates and momentum coefficients. Code is available at https://github.com/zhuchen03/gradinit.

cs.LG↗

arXiv2021

VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization

Most state-of-the-art Graph Neural Networks (GNNs) can be defined as a form of graph convolution which can be realized by message passing between direct neighbors or beyond. To scale such GNNs to large graphs, various neighbor-, layer-, or subgraph-sampling techniques are proposed to alleviate the "neighbor explosion" problem by considering only a small subset of messages passed to the nodes in a mini-batch. However, sampling-based methods are difficult to apply to GNNs that utilize many-hops-away or global context each layer, show unstable performance for different tasks and datasets, and do not speed up model inference. We propose a principled and fundamentally different approach, VQ-GNN, a universal framework to scale up any convolution-based GNNs using Vector Quantization (VQ) without compromising the performance. In contrast to sampling-based techniques, our approach can effectively preserve all the messages passed to a mini-batch of nodes by learning and updating a small number of quantized reference vectors of global node representations, using VQ within each GNN layer. Our framework avoids the "neighbor explosion" problem of GNNs using quantized representations combined with a low-rank version of the graph convolution matrix. We show that such a compact low-rank version of the gigantic convolution matrix is sufficient both theoretically and experimentally. In company with VQ, we design a novel approximated message passing algorithm and a nontrivial back-propagation rule for our framework. Experiments on various types of GNN backbones demonstrate the scalability and competitive performance of our framework on large-graph node classification and link prediction benchmarks.

cs.LG↗

arXiv2021

Understanding the Role of Self-Supervised Learning in Out-of-Distribution Detection Task

Self-supervised learning (SSL) has achieved great success in a variety of computer vision tasks. However, the mechanism of how SSL works in these tasks remains a mystery. In this paper, we study how SSL can enhance the performance of the out-of-distribution (OOD) detection task. We first point out two general properties that a good OOD detector should have: 1) the overall feature space should be large and 2) the inlier feature space should be small. Then we demonstrate that SSL can indeed increase the intrinsic dimension of the overall feature space. In the meantime, SSL even has the potential to shrink the inlier feature space. As a result, there will be more space spared for the outliers, making OOD detection much easier. The conditions when SSL can shrink the inlier feature space is also discussed and validated. By understanding the role of SSL in the OOD detection task, our study can provide a guideline for designing better OOD detection algorithms. Moreover, this work can also shed light to other tasks where SSL can improve the performance.

cs.CV↗

arXiv2021

A Field Guide to Federated Optimization

Federated learning and analytics are a distributed approach for collaboratively learning models (or statistics) from decentralized data, motivated by and designed for privacy protection. The distributed learning process can be formulated as solving federated optimization problems, which emphasize communication efficiency, data heterogeneity, compatibility with privacy and system requirements, and other constraints that are not primary considerations in other problem settings. This paper provides recommendations and guidelines on formulating, designing, evaluating and analyzing federated optimization algorithms through concrete examples and practical implementation, with a focus on conducting effective simulations to infer real-world performance. The goal of this work is not to survey the current literature, but to inspire researchers and practitioners to design federated learning algorithms that can be used in various practical applications.

cs.LG↗

arXiv2021

MaxVA: Fast Adaptation of Step Sizes by Maximizing Observed Variance of Gradients

Adaptive gradient methods such as RMSProp and Adam use exponential moving estimate of the squared gradient to compute adaptive step sizes, achieving better convergence than SGD in face of noisy objectives. However, Adam can have undesirable convergence behaviors due to unstable or extreme adaptive learning rates. Methods such as AMSGrad and AdaBound have been proposed to stabilize the adaptive learning rates of Adam in the later stage of training, but they do not outperform Adam in some practical tasks such as training Transformers \cite{transformer}. In this paper, we propose an adaptive learning rate principle, in which the running mean of squared gradient in Adam is replaced by a weighted mean, with weights chosen to maximize the estimated variance of each coordinate. This results in a faster adaptation to the local gradient variance, which leads to more desirable empirical convergence behaviors than Adam. We prove the proposed algorithm converges under mild assumptions for nonconvex stochastic optimization problems, and demonstrate the improved efficacy of our adaptive averaging approach on machine translation, natural language understanding and large-batch pretraining of BERT. The code is available at https://github.com/zhuchen03/MaxVA.

cs.LG↗

arXiv2021

Inductive Predictions of Extreme Hydrologic Events in The Wabash River Watershed

We present a machine learning method to predict extreme hydrologic events from spatially and temporally varying hydrological and meteorological data. We used a timestep reduction technique to reduce the computational and memory requirements and trained a bidirection LSTM network to predict soil water and stream flow from time series data observed and simulated over eighty years in the Wabash River Watershed. We show that our simple model can be trained much faster than complex attention networks such as GeoMAN without sacrificing accuracy. Based on the predicted values of soil water and stream flow, we predict the occurrence and severity of extreme hydrologic events such as droughts. We also demonstrate that extreme events can be predicted in geographical locations separate from locations observed during the training process. This spatially-inductive setting enables us to predict extreme events in other areas in the US and other parts of the world using our model trained with the Wabash Basin data.

cs.LG↗

arXiv2021

The Intrinsic Dimension of Images and Its Impact on Learning

It is widely believed that natural image data exhibits low-dimensional structure despite the high dimensionality of conventional pixel representations. This idea underlies a common intuition for the remarkable success of deep learning in computer vision. In this work, we apply dimension estimation tools to popular datasets and investigate the role of low-dimensional structure in deep learning. We find that common natural image datasets indeed have very low intrinsic dimension relative to the high number of pixels in the images. Additionally, we find that low dimensional datasets are easier for neural networks to learn, and models solving these tasks generalize better from training to test data. Along the way, we develop a technique for validating our dimension estimation tools on synthetic data generated by GANs allowing us to actively manipulate the intrinsic dimension by controlling the image generation process. Code for our experiments may be found here https://github.com/ppope/dimensions.

cs.CV↗

arXiv2021

Reducing the Teacher-Student Gap via Spherical Knowledge Disitllation

Knowledge distillation aims at obtaining a compact and effective model by learning the mapping function from a much larger one. Due to the limited capacity of the student, the student would underfit the teacher. Therefore, student performance would unexpectedly drop when distilling from an oversized teacher, termed the capacity gap problem. We investigate this problem by study the gap of confidence between teacher and student. We find that the magnitude of confidence is not necessary for knowledge distillation and could harm the student performance if the student are forced to learn confidence. We propose Spherical Knowledge Distillation to eliminate this gap explicitly, which eases the underfitting problem. We find this novel knowledge representation can improve compact models with much larger teachers and is robust to temperature. We conducted experiments on both CIFAR100 and ImageNet, and achieve significant improvement. Specifically, we train ResNet18 to 73.0 accuracy, which is a substantial improvement over previous SOTA and is on par with resnet34 almost twice the student size. The implementation has been shared at https://github.com/forjiuzhou/Spherical-Knowledge-Distillation.

cs.LG↗

arXiv2020

LAMP: Label Augmented Multimodal Pretraining

Multi-modal representation learning by pretraining has become an increasing interest due to its easy-to-use and potential benefit for various Visual-and-Language~(V-L) tasks. However its requirement of large volume and high-quality vision-language pairs highly hinders its values in practice. In this paper, we proposed a novel label-augmented V-L pretraining model, named LAMP, to address this problem. Specifically, we leveraged auto-generated labels of visual objects to enrich vision-language pairs with fine-grained alignment and correspondingly designed a novel pretraining task. Besides, we also found such label augmentation in second-stage pretraining would further universally benefit various downstream tasks. To evaluate LAMP, we compared it with some state-of-the-art models on four downstream tasks. The quantitative results and analysis have well proven the value of labels in V-L pretraining and the effectiveness of LAMP.

cs.MM↗