Graph Neural Networks (GNNs) have become increasingly popular and achieved impressive results in many graph-based applications. However, extensive manual work and domain knowledge are required to design effective architectures, and the results of GNN models have high variance with different training setups, which limits the application of existing GNN models. In this paper, we present AutoHEnsGNN, a framework to build effective and robust models for graph tasks without any human intervention. AutoHEnsGNN won first place in the AutoGraph Challenge for KDD Cup 2020, and achieved the best rank score of five real-life datasets in the final phase. Given a task, AutoHEnsGNN first applies a fast proxy evaluation to automatically select a pool of promising GNN models. Then it builds a hierarchical ensemble framework: 1) We propose graph self-ensemble (GSE), which can reduce the variance of weight initialization and efficiently exploit the information of local and global neighborhoods; 2) Based on GSE, a weighted ensemble of different types of GNN models is used to effectively learn more discriminative node representations. To efficiently search the architectures and ensemble weights, we propose AutoHEnsGNN$_{\text{Gradient}}$, which treats the architectures and ensemble weights as architecture parameters and uses gradient-based architecture search to obtain optimal configurations, and AutoHEnsGNN$_{\text{Adaptive}}$, which can adaptively adjust the ensemble weight based on the model accuracy. Extensive experiments on node classification, graph classification, edge prediction and KDD Cup challenge demonstrate the effectiveness and generality of AutoHEnsGNN
Benefiting from expanding cloud infrastructure, deep neural networks (DNNs) today have increasingly high performance when trained in the cloud. Researchers spend months of effort competing for an extra few percentage points of model accuracy. However, when these models are actually deployed on edge devices in practice, very often, the performance can abruptly drop over 10% without obvious reasons. The key challenge is that there is not much visibility into ML inference execution on edge devices, and very little awareness of potential issues during the edge deployment process. We present ML-EXray, an end-to-end framework, which provides visibility into layer-level details of the ML execution, and helps developers analyze and debug cloud-to-edge deployment issues. More often than not, the reason for sub-optimal edge performance does not only lie in the model itself, but every operation throughout the data flow and the deployment process. Evaluations show that ML-EXray can effectively catch deployment issues, such as pre-processing bugs, quantization issues, suboptimal kernels, etc. Using ML-EXray, users need to write less than 15 lines of code to fully examine the edge deployment pipeline. Eradicating these issues, ML-EXray can correct model performance by up to 30%, pinpoint error-prone layers, and guide users to optimize kernel execution latency by two orders of magnitude. Code and APIs will be released as an open-source multi-lingual instrumentation library and a Python deployment validation library.
In this paper, we place the atomic action detection problem into a Long-Short Term Context (LSTC) to analyze how the temporal reliance among video signals affect the action detection results. To do this, we decompose the action recognition pipeline into short-term and long-term reliance, in terms of the hypothesis that the two kinds of context are conditionally independent given the objective action instance. Within our design, a local aggregation branch is utilized to gather dense and informative short-term cues, while a high order long-term inference branch is designed to reason the objective action class from high-order interaction between actor and other person or person pairs. Both branches independently predict the context-specific actions and the results are merged in the end. We demonstrate that both temporal grains are beneficial to atomic action recognition. On the mainstream benchmarks of atomic action detection, our design can bring significant performance gain from the existing state-of-the-art pipeline. The code of this project can be found at [this url](https://github.com/TencentYoutuResearch/ActionDetection-LSTC)
The few-shot natural language understanding (NLU) task has attracted much recent attention. However, prior methods have been evaluated under a disparate set of protocols, which hinders fair comparison and measuring progress of the field. To address this issue, we introduce an evaluation framework that improves previous evaluation procedures in three key aspects, i.e., test performance, dev-test correlation, and stability. Under this new evaluation framework, we re-evaluate several state-of-the-art few-shot methods for NLU tasks. Our framework reveals new insights: (1) both the absolute performance and relative gap of the methods were not accurately estimated in prior literature; (2) no single method dominates most tasks with consistent performance; (3) improvements of some methods diminish with a larger pretrained model; and (4) gains from different methods are often complementary and the best combined model performs close to a strong fully-supervised baseline. We open-source our toolkit, FewNLU, that implements our evaluation framework along with a number of state-of-the-art methods.
We study a finite-horizon restless multi-armed bandit problem with multiple actions, dubbed R(MA)^2B. The state of each arm evolves according to a controlled Markov decision process (MDP), and the reward of pulling an arm depends on both the current state of the corresponding MDP and the action taken. The goal is to sequentially choose actions for arms so as to maximize the expected value of the cumulative rewards collected. Since finding the optimal policy is typically intractable, we propose a computationally appealing index policy which we call Occupancy-Measured-Reward Index Policy. Our policy is well-defined even if the underlying MDPs are not indexable. We prove that it is asymptotically optimal when the activation budget and number of arms are scaled up, while keeping their ratio as a constant. For the case when the system parameters are unknown, we develop a learning algorithm. Our learning algorithm uses the principle of optimism in the face of uncertainty and further uses a generative model in order to fully exploit the structure of Occupancy-Measured-Reward Index Policy. We call it the R(MA)^2B-UCB algorithm. As compared with the existing algorithms, R(MA)^2B-UCB performs close to an offline optimum policy, and also achieves a sub-linear regret with a low computational complexity. Experimental results show that R(MA)^2B-UCB outperforms the existing algorithms in both regret and run time.
Federated learning (FL) is a popular technique to train machine learning (ML) models with decentralized data. Extensive works have studied the performance of the global model; however, it is still unclear how the training process affects the final test accuracy. Exacerbating this problem is the fact that FL executions differ significantly from traditional ML with heterogeneous data characteristics across clients, involving more hyperparameters. In this work, we show that the final test accuracy of FL is dramatically affected by the early phase of the training process, i.e., FL exhibits critical learning periods, in which small gradient errors can have irrecoverable impact on the final test accuracy. To further explain this phenomenon, we generalize the trace of the Fisher Information Matrix (FIM) to FL and define a new notion called FedFIM, a quantity reflecting the local curvature of each clients from the beginning of the training in FL. Our findings suggest that the {\em initial learning phase} plays a critical role in understanding the FL performance. This is in contrast to many existing works which generally do not connect the final accuracy of FL to the early phase training. Finally, seizing critical learning periods in FL is of independent interest and could be useful for other problems such as the choices of hyperparameters such as the number of client selected per round, batch size, and more, so as to improve the performance of FL training and testing.
Open-domain Question Answering (ODQA) has achieved significant results in terms of supervised learning manner. However, data annotation cannot also be irresistible for its huge demand in an open domain. Though unsupervised QA or unsupervised Machine Reading Comprehension (MRC) has been tried more or less, unsupervised ODQA has not been touched according to our best knowledge. This paper thus pioneers the work of unsupervised ODQA by formally introducing the task and proposing a series of key data construction methods. Our exploration in this work inspiringly shows unsupervised ODQA can reach up to 86% performance of supervised ones.
Weight sharing has become the \textit{de facto} approach to reduce the training cost of neural architecture search (NAS) by reusing the weights of shared operators from previously trained child models. However, the estimated accuracy of those child models has a low rank correlation with the ground truth accuracy due to the interference among different child models caused by weight sharing. In this paper, we investigate the interference issue by sampling different child models and calculating the gradient similarity of shared operators, and observe that: 1) the interference on a shared operator between two child models is positively correlated to the number of different operators between them; 2) the interference is smaller when the inputs and outputs of the shared operator are more similar. Inspired by these two observations, we propose two approaches to mitigate the interference: 1) rather than randomly sampling child models for optimization, we propose a gradual modification scheme by modifying one operator between adjacent optimization steps to minimize the interference on the shared operators; 2) forcing the inputs and outputs of the operator across all child models to be similar to reduce the interference. Experiments on a BERT search space verify that mitigating interference via each of our proposed methods improves the rank correlation of super-pet and combining both methods can achieve better results. Our searched architecture outperforms RoBERTa$_{\rm base}$ by 1.1 and 0.6 scores and ELECTRA$_{\rm base}$ by 1.6 and 1.1 scores on the dev and test set of GLUE benchmark. Extensive results on the BERT compression task, SQuAD datasets and other search spaces also demonstrate the effectiveness and generality of our proposed methods.
Serverless computing has become a new cloud computing paradigm that promises to deliver high cost-efficiency and simplified cloud deployment with automated resource scaling at a fine granularity. Users decouple a cloud application into chained functions and preset each serverless function's memory and CPU demands at megabyte-level and core-level, respectively. Serverless platforms then automatically scale the number of functions to accommodate the workloads. However, the complexities of chained functions make it non-trivial to accurately determine the resource demands of each function for users, leading to either resource over-provision or under-provision for individual functions. This paper presents FaaSRM, a new resource manager (RM) for serverless platforms that maximizes resource efficiency by dynamically harvesting idle resources from functions over-supplied to functions under-supplied. FaaSRM monitors each function's resource utilization in real-time, detects over-provisioning and under-provisioning, and applies deep reinforcement learning to harvest idle resources safely using a safeguard mechanism and accelerate functions efficiently. We have implemented and deployed a FaaSRM prototype in a 13-node Apache OpenWhisk cluster. Experimental results on the OpenWhisk cluster show that FaaSRM reduces the execution time of 98% of function invocations by 35.81% compared to the baseline RMs by harvesting idle resources from 38.8% of the invocations and accelerating 39.2% of the invocations.
Most previous methods for text data augmentation are limited to simple tasks and weak baselines. We explore data augmentation on hard tasks (i.e., few-shot natural language understanding) and strong baselines (i.e., pretrained models with over one billion parameters). Under this setting, we reproduced a large number of previous augmentation methods and found that these methods bring marginal gains at best and sometimes degrade the performance much. To address this challenge, we propose a novel data augmentation method FlipDA that jointly uses a generative model and a classifier to generate label-flipped data. Central to the idea of FlipDA is the discovery that generating label-flipped data is more crucial to the performance than generating label-preserved data. Experiments show that FlipDA achieves a good tradeoff between effectiveness and robustness---it substantially improves many tasks while not negatively affecting the others.