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

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Topic": models, code, and papers

An Interpretable Graph-based Mapping of Trustworthy Machine Learning Research

May 13, 2021
Noemi Derzsy, Subhabrata Majumdar, Rajat Malik

There is an increasing interest in ensuring machine learning (ML) frameworks behave in a socially responsible manner and are deemed trustworthy. Although considerable progress has been made in the field of Trustworthy ML (TwML) in the recent past, much of the current characterization of this progress is qualitative. Consequently, decisions about how to address issues of trustworthiness and future research goals are often left to the interested researcher. In this paper, we present the first quantitative approach to characterize the comprehension of TwML research. We build a co-occurrence network of words using a web-scraped corpus of more than 7,000 peer-reviewed recent ML papers -- consisting of papers both related and unrelated to TwML. We use community detection to obtain semantic clusters of words in this network that can infer relative positions of TwML topics. We propose an innovative fingerprinting algorithm to obtain probabilistic similarity scores for individual words, then combine them to give a paper-level relevance score. The outcomes of our analysis inform a number of interesting insights on advancing the field of TwML research.

* Accepted in CompleNet-2021 (oral presentation) 

  Access Paper or Ask Questions

On the Theory of Stochastic Automata

Mar 26, 2021
Merve Nur Cakir, Mehwish Saleemi, Karl-Heinz Zimmermann

The theory of discrete stochastic systems has been initiated by the work of Shannon and von Neumann. While Shannon has considered memory-less communication channels and their generalization by introducing states, von Neumann has studied the synthesis of reliable systems from unreliable components. The fundamental work of Rabin and Scott about deterministic finite-state automata has led to two generalizations. First, the generalization of transition functions to conditional distributions studied by Carlyle and Starke. This in turn has led to a generalization of time-discrete Markov chains in which the chains are governed by more than one transition probability matrix. Second, the generalization of regular sets by introducing stochastic automata as described by Rabin. Stochastic automata are well-investigated. This report provides a short introduction to stochastic automata based on the valuable book of Claus. This includes the basic topics of the theory of stochastic automata: equivalence, minimization, reduction, covering, observability, and determinism. Then stochastic versions of Mealy and Moore automata are studied and finally stochastic language acceptors are considered as a generalization of nondeterministic finite-state acceptors.

* 50 pages, 11 figures, index included 

  Access Paper or Ask Questions

UniFuse: Unidirectional Fusion for 360$^{\circ}$ Panorama Depth Estimation

Feb 06, 2021
Hualie Jiang, Zhe Sheng, Siyu Zhu, Zilong Dong, Rui Huang

Learning depth from spherical panoramas is becoming a popular research topic because a panorama has a full field-of-view of the environment and provides a relatively complete description of a scene. However, applying well-studied CNNs for perspective images to the standard representation of spherical panoramas, i.e., the equirectangular projection, is suboptimal, as it becomes distorted towards the poles. Another representation is the cubemap projection, which is distortion-free but discontinued on edges and limited in the field-of-view. This paper introduces a new framework to fuse features from the two projections, unidirectionally feeding the cubemap features to the equirectangular features only at the decoding stage. Unlike the recent bidirectional fusion approach operating at both the encoding and decoding stages, our fusion scheme is much more efficient. Besides, we also designed a more effective fusion module for our fusion scheme. Experiments verify the effectiveness of our proposed fusion strategy and module, and our model achieves state-of-the-art performance on four popular datasets. Additional experiments show that our model also has the advantages of model complexity and generalization capability.

* 9 pages; 5 figures; accepted by IEEE Robotics and Automation Letters; Demo: 

  Access Paper or Ask Questions

Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies

Jan 06, 2021
Mor Geva, Daniel Khashabi, Elad Segal, Tushar Khot, Dan Roth, Jonathan Berant

A key limitation in current datasets for multi-hop reasoning is that the required steps for answering the question are mentioned in it explicitly. In this work, we introduce StrategyQA, a question answering (QA) benchmark where the required reasoning steps are implicit in the question, and should be inferred using a strategy. A fundamental challenge in this setup is how to elicit such creative questions from crowdsourcing workers, while covering a broad range of potential strategies. We propose a data collection procedure that combines term-based priming to inspire annotators, careful control over the annotator population, and adversarial filtering for eliminating reasoning shortcuts. Moreover, we annotate each question with (1) a decomposition into reasoning steps for answering it, and (2) Wikipedia paragraphs that contain the answers to each step. Overall, StrategyQA includes 2,780 examples, each consisting of a strategy question, its decomposition, and evidence paragraphs. Analysis shows that questions in StrategyQA are short, topic-diverse, and cover a wide range of strategies. Empirically, we show that humans perform well (87%) on this task, while our best baseline reaches an accuracy of $\sim$66%.

* Accepted for publication in Transactions of the Association for Computational Linguistics (TACL), 2021. Author's final version 

  Access Paper or Ask Questions

Leaf Segmentation and Counting with Deep Learning: on Model Certainty, Test-Time Augmentation, Trade-Offs

Dec 21, 2020
Douglas Pinto Sampaio Gomes, Lihong Zheng

Plant phenotyping tasks such as leaf segmentation and counting are fundamental to the study of phenotypic traits. Since it is well-suited for these tasks, deep supervised learning has been prevalent in recent works proposing better performing models at segmenting and counting leaves. Despite good efforts from research groups, one of the main challenges for proposing better methods is still the limitation of labelled data availability. The main efforts of the field seem to be augmenting existing limited data sets, and some aspects of the modelling process have been under-discussed. This paper explores such topics and present experiments that led to the development of the best-performing method in the Leaf Segmentation Challenge and in another external data set of Komatsuna plants. The model has competitive performance while been arguably simpler than other recently proposed ones. The experiments also brought insights such as the fact that model cardinality and test-time augmentation may have strong applications in object segmentation of single class and high occlusion, and regarding the data distribution of recently proposed data sets for benchmarking.

  Access Paper or Ask Questions

DeepCloth: Neural Garment Representation for Shape and Style Editing

Nov 30, 2020
Zhaoqi Su, Tao Yu, Yangang Wang, Yipeng Li, Yebin Liu

Garment representation, animation and editing is a challenging topic in the area of computer vision and graphics. Existing methods cannot perform smooth and reasonable garment transition under different shape styles and topologies. In this work, we introduce a novel method, termed as DeepCloth, to establish a unified garment representation framework enabling free and smooth garment style transition. Our key idea is to represent garment geometry by a "UV-position map with mask", which potentially allows the description of various garments with different shapes and topologies. Furthermore, we learn a continuous feature space mapped from the above UV space, enabling garment shape editing and transition by controlling the garment features. Finally, we demonstrate applications of garment animation, reconstruction and editing based on our neural garment representation and encoding method. To conclude, with the proposed DeepCloth, we move a step forward on establishing a more flexible and general 3D garment digitization framework. Experiments demonstrate that our method can achieve the state-of-the-art garment modeling results compared with the previous methods.

  Access Paper or Ask Questions

Adaptive Neuro-Fuzzy Inference System and a Multilayer Perceptron Model Trained with Grey Wolf Optimizer for Predicting Solar Diffuse Fraction

Sep 13, 2020
Randall Claywell, Laszlo Nadai, Felde Imre, Amir Mosavi

The accurate prediction of the solar Diffuse Fraction (DF), sometimes called the Diffuse Ratio, is an important topic for solar energy research. In the present study, the current state of Diffuse Irradiance research is discussed and then three robust, Machine Learning (ML) models, are examined using a large dataset (almost 8 years) of hourly readings from Almeria, Spain. The ML models used herein, are a hybrid Adaptive Network-based Fuzzy Inference System (ANFIS), a single Multi-Layer Perceptron (MLP) and a hybrid Multi-Layer Perceptron-Grey Wolf Optimizer (MLP-GWO). These models were evaluated for their predictive precision, using various Solar and Diffuse Fraction (DF) irradiance data, from Spain. The results were then evaluated using two frequently used evaluation criteria, the Mean Absolute Error (MAE) and the Root Mean Square Error (RMSE). The results showed that the MLP-GWO model, followed by the ANFIS model, provided a higher performance, in both the training and the testing procedures.

* 13 pages, 6 figures 

  Access Paper or Ask Questions

Adversarial Learning for Counterfactual Fairness

Aug 30, 2020
Vincent Grari, Sylvain Lamprier, Marcin Detyniecki

In recent years, fairness has become an important topic in the machine learning research community. In particular, counterfactual fairness aims at building prediction models which ensure fairness at the most individual level. Rather than globally considering equity over the entire population, the idea is to imagine what any individual would look like with a variation of a given attribute of interest, such as a different gender or race for instance. Existing approaches rely on Variational Auto-encoding of individuals, using Maximum Mean Discrepancy (MMD) penalization to limit the statistical dependence of inferred representations with their corresponding sensitive attributes. This enables the simulation of counterfactual samples used for training the target fair model, the goal being to produce similar outcomes for every alternate version of any individual. In this work, we propose to rely on an adversarial neural learning approach, that enables more powerful inference than with MMD penalties, and is particularly better fitted for the continuous setting, where values of sensitive attributes cannot be exhaustively enumerated. Experiments show significant improvements in term of counterfactual fairness for both the discrete and the continuous settings.

* 11 pages, 5 figures 

  Access Paper or Ask Questions

BBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy Network

Jul 06, 2020
Fan Deng-Ping, Zhai Yingjie, Borji Ali, Yang Jufeng, Shao Ling

Multi-level feature fusion is a fundamental topic in computer vision for detecting, segmenting, and classifying objects at various scales. When multi-level features meet multi-modal cues, the optimal fusion problem becomes a hot potato. In this paper, we make the first attempt to leverage the inherent multi-modal and multi-level nature of RGB-D salient object detection to develop a novel cascaded refinement network. In particular, we 1) propose a bifurcated backbone strategy (BBS) to split the multi-level features into teacher and student features, and 2) utilize a depth-enhanced module (DEM) to excavate informative parts of depth cues from the channel and spatial views. This fuses RGB and depth modalities in a complementary way. Our simple yet efficient architecture, dubbed Bifurcated Backbone Strategy Network (BBS-Net), is backbone independent, runs in real-time (48 fps), and significantly outperforms 18 SOTAs on seven challenging datasets using four metrics.

* Accepted in ECCV2020. Code: 

  Access Paper or Ask Questions

An ensemble learning framework based on group decision making

Jul 01, 2020
Jingyi He, Xiaojun Zhou, Rundong Zhang, Chunhua Yang

The classification problem is a significant topic in machine learning which aims to teach machines how to group together data by particular criteria. In this paper, a framework for the ensemble learning (EL) method based on group decision making (GDM) has been proposed to resolve this issue. In this framework, base learners can be considered as decision-makers, different categories can be seen as alternatives, classification results obtained by diverse base learners can be considered as performance ratings, and the precision, recall, and accuracy which can reflect the performances of the classification methods can be employed to identify the weights of decision-makers in GDM. Moreover, considering that the precision and recall defined in binary classification problems can not be used directly in the multi-classification problem, the One vs Rest (OvR) has been proposed to obtain the precision and recall of the base learner for each category. The experimental results demonstrate that the proposed EL method based on GDM has higher accuracy than other 6 current popular classification methods in most instances, which verifies the effectiveness of the proposed method.

* 6 pages, 2 figures 

  Access Paper or Ask Questions