Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Recommendation": models, code, and papers

Graph Convolutional Networks against Degree-Related Biases

Jun 28, 2020
Xianfeng Tang, Huaxiu Yao, Yiwei Sun, Yiqi Wang, Jiliang Tang, Charu Aggarwal, Prasenjit Mitra, Suhang Wang

In recent years, Graph Convolutional Networks (GCNs) show competitive performance in different domains, such as social network analysis, recommendation, and smart city. However, training GCNs with insufficient supervision is very difficult. The performance of GCNs becomes unsatisfying with few labeled data. Although some pioneering work try to understand why GCNs work or fail, their analysis focus more on the entire model level. Profiling GCNs on different nodes is still underexplored. To address the limitations, we study GCNs with respect to the node degree distribution. We show that GCNs have a higher accuracy on nodes with larger degrees even if they are underrepresented in most graphs, with both empirical observation and theoretical proof. We then propose Self-Supervised-Learning Degree-Specific GCN (SL-DSGCN) which handles the degree-related biases of GCNs from model and data aspects. Firstly, we design a degree-specific GCN layer that models both discrepancies and similarities of nodes with different degrees, and reduces the inner model-aspect biases of GCNs caused by sharing the same parameters with all nodes. Secondly, we develop a self-supervised-learning algorithm that assigns pseudo labels with uncertainty scores on unlabeled nodes using a Bayesian neural network. Pseudo labels increase the chance of connecting to labeled neighbors for low-degree nodes, thus reducing the biases of GCNs from the data perspective. We further exploit uncertainty scores as dynamic weights on pseudo labels in the stochastic gradient descent for SL-DSGCN. We validate \ours on three benchmark datasets, and confirm SL-DSGCN not only outperforms state-of-the-art self-training/self-supervised-learning GCN methods, but also improves GCN accuracy dramatically for low-degree nodes.

* Preprint, under review 

  Access Paper or Ask Questions

Systematic Comparison of the Influence of Different Data Preprocessing Methods on the Classification of Gait Using Machine Learning

Nov 11, 2019
Johannes Burdack, Fabian Horst, Sven Giesselbach, Ibrahim Hassan, Sabrina Daffner, Wolfgang I. Schöllhorn

Human movements are characterized by highly non-linear and multi-dimensional interactions within the motor system. Recently, an increasing emphasis on machine-learning applications has led to a significant contribution to the field of gait analysis e.g. in increasing the classification accuracy. In order to ensure the generalizability of the machine-learning models, different data preprocessing steps are usually carried out to process the measured raw data before the classifications. In the past, various methods have been used for each of these preprocessing steps. However, there are hardly any standard procedures or rather systematic comparisons of these different methods and their impact on the classification accuracy. Therefore, the aim of this analysis is to compare different combinations of commonly applied data preprocessing steps and test their effects on the classification accuracy of gait patterns. A publicly available dataset on intra-individual changes of gait patterns was used for this analysis. Forty-two healthy subjects performed 6 sessions of 15 gait trials for one day. For each trial, two force plates recorded the 3D ground reaction forces (GRF). The data was preprocessed with the following steps: GRF filtering, time derivative, time normalization, data reduction, weight normalization and data scaling. Subsequently, combinations of all methods from each individual preprocessing step were analyzed and compared with respect to their prediction accuracy in a six-session classification using Support Vector Machines, Random Forest Classifiers and Multi-Layer Perceptrons. In conclusion, the present results provide first domain-specific recommendations for commonly applied data preprocessing methods and might help to build more comparable and more robust classification models based on machine learning that are suitable for a practical application.

* 17 pages, 3 figures, 4 tables 

  Access Paper or Ask Questions

Willump: A Statistically-Aware End-to-end Optimizer for Machine Learning Inference

Jun 03, 2019
Peter Kraft, Daniel Kang, Deepak Narayanan, Shoumik Palkar, Peter Bailis, Matei Zaharia

Machine learning (ML) has become increasingly important and performance-critical in modern data centers. This has led to interest in model serving systems, which perform ML inference and serve predictions to end-user applications. However, most existing model serving systems approach ML inference as an extension of conventional data serving workloads and miss critical opportunities for performance. In this paper, we present Willump, a statistically-aware optimizer for ML inference that takes advantage of key properties of ML inference not shared by traditional workloads. First, ML models can often be approximated efficiently on many "easy" inputs by judiciously using a less expensive model for these inputs (e.g., not computing all the input features). Willump automatically generates such approximations from an ML inference pipeline, providing up to 4.1$\times$ speedup without statistically significant accuracy loss. Second, ML models are often used in higher-level end-to-end queries in an ML application, such as computing the top K predictions for a recommendation model. Willump optimizes inference based on these higher-level queries by up to 5.7$\times$ over na\"ive batch inference. Willump combines these novel optimizations with standard compiler optimizations and a computation graph-aware feature caching scheme to automatically generate fast inference code for ML pipelines. We show that Willump improves performance of real-world ML inference pipelines by up to 23$\times$, with its novel optimizations giving 3.6-5.7$\times$ speedups over compilation. We also show that Willump integrates easily with existing model serving systems, such as Clipper.

  Access Paper or Ask Questions

Fast Genetic Algorithms

Mar 15, 2017
Benjamin Doerr, Huu Phuoc Le, Régis Makhmara, Ta Duy Nguyen

For genetic algorithms using a bit-string representation of length~$n$, the general recommendation is to take $1/n$ as mutation rate. In this work, we discuss whether this is really justified for multimodal functions. Taking jump functions and the $(1+1)$ evolutionary algorithm as the simplest example, we observe that larger mutation rates give significantly better runtimes. For the $\jump_{m,n}$ function, any mutation rate between $2/n$ and $m/n$ leads to a speed-up at least exponential in $m$ compared to the standard choice. The asymptotically best runtime, obtained from using the mutation rate $m/n$ and leading to a speed-up super-exponential in $m$, is very sensitive to small changes of the mutation rate. Any deviation by a small $(1 \pm \eps)$ factor leads to a slow-down exponential in $m$. Consequently, any fixed mutation rate gives strongly sub-optimal results for most jump functions. Building on this observation, we propose to use a random mutation rate $\alpha/n$, where $\alpha$ is chosen from a power-law distribution. We prove that the $(1+1)$ EA with this heavy-tailed mutation rate optimizes any $\jump_{m,n}$ function in a time that is only a small polynomial (in~$m$) factor above the one stemming from the optimal rate for this $m$. Our heavy-tailed mutation operator yields similar speed-ups (over the best known performance guarantees) for the vertex cover problem in bipartite graphs and the matching problem in general graphs. Following the example of fast simulated annealing, fast evolution strategies, and fast evolutionary programming, we propose to call genetic algorithms using a heavy-tailed mutation operator \emph{fast genetic algorithms}.

* Proceedings of GECCO 2017 

  Access Paper or Ask Questions

Mitigating Divergence of Latent Factors via Dual Ascent for Low Latency Event Prediction Models

Nov 15, 2021
Alex Shtoff, Yair Koren

Real-world content recommendation marketplaces exhibit certain behaviors and are imposed by constraints that are not always apparent in common static offline data sets. One example that is common in ad marketplaces is swift ad turnover. New ads are introduced and old ads disappear at high rates every day. Another example is ad discontinuity, where existing ads may appear and disappear from the market for non negligible amounts of time due to a variety of reasons (e.g., depletion of budget, pausing by the advertiser, flagging by the system, and more). These behaviors sometimes cause the model's loss surface to change dramatically over short periods of time. To address these behaviors, fresh models are highly important, and to achieve this (and for several other reasons) incremental training on small chunks of past events is often employed. These behaviors and algorithmic optimizations occasionally cause model parameters to grow uncontrollably large, or \emph{diverge}. In this work present a systematic method to prevent model parameters from diverging by imposing a carefully chosen set of constraints on the model's latent vectors. We then devise a method inspired by primal-dual optimization algorithms to fulfill these constraints in a manner which both aligns well with incremental model training, and does not require any major modifications to the underlying model training algorithm. We analyze, demonstrate, and motivate our method on OFFSET, a collaborative filtering algorithm which drives Yahoo native advertising, which is one of VZM's largest and faster growing businesses, reaching a run-rate of many hundreds of millions USD per year. Finally, we conduct an online experiment which shows a substantial reduction in the number of diverging instances, and a significant improvement to both user experience and revenue.

* 10 pages. Accepted to IEEE BigData 2021 

  Access Paper or Ask Questions

What is Semantic Communication? A View on Conveying Meaning in the Era of Machine Intelligence

Oct 01, 2021
Qiao Lan, Dingzhu Wen, Zezhong Zhang, Qunsong Zeng, Xu Chen, Petar Popovski, Kaibin Huang

In 1940s, Claude Shannon developed the information theory focusing on quantifying the maximum data rate that can be supported by a communication channel. Guided by this, the main theme of wireless system design up until 5G was the data rate maximization. In his theory, the semantic aspect and meaning of messages were treated as largely irrelevant to communication. The classic theory started to reveal its limitations in the modern era of machine intelligence, consisting of the synergy between IoT and AI. By broadening the scope of the classic framework, in this article we present a view of semantic communication (SemCom) and conveying meaning through the communication systems. We address three communication modalities, human-to-human (H2H), human-to-machine (H2M), and machine-to-machine (M2M) communications. The latter two, the main theme of the article, represent the paradigm shift in communication and computing. H2M SemCom refers to semantic techniques for conveying meanings understandable by both humans and machines so that they can interact. M2M SemCom refers to effectiveness techniques for efficiently connecting machines such that they can effectively execute a specific computation task in a wireless network. The first part of the article introduces SemCom principles including encoding, system architecture, and layer-coupling and end-to-end design approaches. The second part focuses on specific techniques for application areas of H2M (human and AI symbiosis, recommendation, etc.) and M2M SemCom (distributed learning, split inference, etc.) Finally, we discuss the knowledge graphs approach for designing SemCom systems. We believe that this comprehensive introduction will provide a useful guide into the emerging area of SemCom that is expected to play an important role in 6G featuring connected intelligence and integrated sensing, computing, communication, and control.

* This is an invited paper for Journal of Communications and Information Networks 

  Access Paper or Ask Questions

Real-Time Patient-Specific ECG Classification by 1D Self-Operational Neural Networks

Sep 30, 2021
Junaid Malik, Ozer Can Devecioglu, Serkan Kiranyaz, Turker Ince, Moncef Gabbouj

Despite the proliferation of numerous deep learning methods proposed for generic ECG classification and arrhythmia detection, compact systems with the real-time ability and high accuracy for classifying patient-specific ECG are still few. Particularly, the scarcity of patient-specific data poses an ultimate challenge to any classifier. Recently, compact 1D Convolutional Neural Networks (CNNs) have achieved the state-of-the-art performance level for the accurate classification of ventricular and supraventricular ectopic beats. However, several studies have demonstrated the fact that the learning performance of the conventional CNNs is limited because they are homogenous networks with a basic (linear) neuron model. In order to address this deficiency and further boost the patient-specific ECG classification performance, in this study, we propose 1D Self-organized Operational Neural Networks (1D Self-ONNs). Due to its self-organization capability, Self-ONNs have the utmost advantage and superiority over conventional ONNs where the prior operator search within the operator set library to find the best possible set of operators is entirely avoided. As the first study where 1D Self-ONNs are ever proposed for a classification task, our results over the MIT-BIH arrhythmia benchmark database demonstrate that 1D Self-ONNs can surpass 1D CNNs with a significant margin while having a similar computational complexity. Under AAMI recommendations and with minimal common training data used, over the entire MIT-BIH dataset 1D Self-ONNs have achieved 98% and 99.04% average accuracies, 76.6% and 93.7% average F1 scores on supra-ventricular and ventricular ectopic beat (VEB) classifications, respectively, which is the highest performance level ever reported.

  Access Paper or Ask Questions

TrUMAn: Trope Understanding in Movies and Animations

Aug 11, 2021
Hung-Ting Su, Po-Wei Shen, Bing-Chen Tsai, Wen-Feng Cheng, Ke-Jyun Wang, Winston H. Hsu

Understanding and comprehending video content is crucial for many real-world applications such as search and recommendation systems. While recent progress of deep learning has boosted performance on various tasks using visual cues, deep cognition to reason intentions, motivation, or causality remains challenging. Existing datasets that aim to examine video reasoning capability focus on visual signals such as actions, objects, relations, or could be answered utilizing text bias. Observing this, we propose a novel task, along with a new dataset: Trope Understanding in Movies and Animations (TrUMAn), intending to evaluate and develop learning systems beyond visual signals. Tropes are frequently used storytelling devices for creative works. By coping with the trope understanding task and enabling the deep cognition skills of machines, we are optimistic that data mining applications and algorithms could be taken to the next level. To tackle the challenging TrUMAn dataset, we present a Trope Understanding and Storytelling (TrUSt) with a new Conceptual Storyteller module, which guides the video encoder by performing video storytelling on a latent space. The generated story embedding is then fed into the trope understanding model to provide further signals. Experimental results demonstrate that state-of-the-art learning systems on existing tasks reach only 12.01% of accuracy with raw input signals. Also, even in the oracle case with human-annotated descriptions, BERT contextual embedding achieves at most 28% of accuracy. Our proposed TrUSt boosts the model performance and reaches 13.94% performance. We also provide detailed analysis to pave the way for future research. TrUMAn is publicly available at:

* CIKM 2021. The first two authors contributed equally to this work 

  Access Paper or Ask Questions

A Survey of Evaluation Metrics Used for NLG Systems

Oct 05, 2020
Ananya B. Sai, Akash Kumar Mohankumar, Mitesh M. Khapra

The success of Deep Learning has created a surge in interest in a wide a range of Natural Language Generation (NLG) tasks. Deep Learning has not only pushed the state of the art in several existing NLG tasks but has also facilitated researchers to explore various newer NLG tasks such as image captioning. Such rapid progress in NLG has necessitated the development of accurate automatic evaluation metrics that would allow us to track the progress in the field of NLG. However, unlike classification tasks, automatically evaluating NLG systems in itself is a huge challenge. Several works have shown that early heuristic-based metrics such as BLEU, ROUGE are inadequate for capturing the nuances in the different NLG tasks. The expanding number of NLG models and the shortcomings of the current metrics has led to a rapid surge in the number of evaluation metrics proposed since 2014. Moreover, various evaluation metrics have shifted from using pre-determined heuristic-based formulae to trained transformer models. This rapid change in a relatively short time has led to the need for a survey of the existing NLG metrics to help existing and new researchers to quickly come up to speed with the developments that have happened in NLG evaluation in the last few years. Through this survey, we first wish to highlight the challenges and difficulties in automatically evaluating NLG systems. Then, we provide a coherent taxonomy of the evaluation metrics to organize the existing metrics and to better understand the developments in the field. We also describe the different metrics in detail and highlight their key contributions. Later, we discuss the main shortcomings identified in the existing metrics and describe the methodology used to evaluate evaluation metrics. Finally, we discuss our suggestions and recommendations on the next steps forward to improve the automatic evaluation metrics.

* A condensed version of this paper is submitted to ACM CSUR 

  Access Paper or Ask Questions