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

The Foundations of Deep Learning with a Path Towards General Intelligence

Jun 22, 2018
Eray Özkural

Like any field of empirical science, AI may be approached axiomatically. We formulate requirements for a general-purpose, human-level AI system in terms of postulates. We review the methodology of deep learning, examining the explicit and tacit assumptions in deep learning research. Deep Learning methodology seeks to overcome limitations in traditional machine learning research as it combines facets of model richness, generality, and practical applicability. The methodology so far has produced outstanding results due to a productive synergy of function approximation, under plausible assumptions of irreducibility and the efficiency of back-propagation family of algorithms. We examine these winning traits of deep learning, and also observe the various known failure modes of deep learning. We conclude by giving recommendations on how to extend deep learning methodology to cover the postulates of general-purpose AI including modularity, and cognitive architecture. We also relate deep learning to advances in theoretical neuroscience research.

* Submitted to AGI 2018 

  Access Paper or Ask Questions

Data Poisoning Attacks on Factorization-Based Collaborative Filtering

Oct 05, 2016
Bo Li, Yining Wang, Aarti Singh, Yevgeniy Vorobeychik

Recommendation and collaborative filtering systems are important in modern information and e-commerce applications. As these systems are becoming increasingly popular in the industry, their outputs could affect business decision making, introducing incentives for an adversarial party to compromise the availability or integrity of such systems. We introduce a data poisoning attack on collaborative filtering systems. We demonstrate how a powerful attacker with full knowledge of the learner can generate malicious data so as to maximize his/her malicious objectives, while at the same time mimicking normal user behavior to avoid being detected. While the complete knowledge assumption seems extreme, it enables a robust assessment of the vulnerability of collaborative filtering schemes to highly motivated attacks. We present efficient solutions for two popular factorization-based collaborative filtering algorithms: the \emph{alternative minimization} formulation and the \emph{nuclear norm minimization} method. Finally, we test the effectiveness of our proposed algorithms on real-world data and discuss potential defensive strategies.

  Access Paper or Ask Questions

ICD 10 Based Medical Expert System Using Fuzzy Temporal Logic

Jan 12, 2010
P. Chinniah, Dr. S. Muttan

Medical diagnosis process involves many levels and considerable amount of time and money are invariably spent for the first level of diagnosis usually made by the physician for all the patients every time. Hence there is a need for a computer based system which not only asks relevant questions to the patients but also aids the physician by giving a set of possible diseases from the symptoms obtained using logic at inference. In this work, an ICD10 based Medical Expert System that provides advice, information and recommendation to the physician using fuzzy temporal logic. The knowledge base used in this system consists of facts of symptoms and rules on diseases. It also provides fuzzy severity scale and weight factor for symptom and disease and can vary with respect to time. The system generates the possible disease conditions based on modified Euclidean metric using Elders algorithm for effective clustering. The minimum similarity value is used as the decision parameter to identify a disease.

* International Journal of Computer Science and Information Security, IJCSIS, Vol. 6, No. 3, pp. 084-089, December 2009, USA 
* 6 pages IEEE format, International Journal of Computer Science and Information Security, IJCSIS December 2009, ISSN 1947 5500, 

  Access Paper or Ask Questions

Learning Expanding Graphs for Signal Interpolation

Mar 15, 2022
Bishwadeep Das, Elvin Isufi

Performing signal processing over graphs requires knowledge of the underlying fixed topology. However, graphs often grow in size with new nodes appearing over time, whose connectivity is typically unknown; hence, making more challenging the downstream tasks in applications like cold start recommendation. We address such a challenge for signal interpolation at the incoming nodes blind to the topological connectivity of the specific node. Specifically, we propose a stochastic attachment model for incoming nodes parameterized by the attachment probabilities and edge weights. We estimate these parameters in a data-driven fashion by relying only on the attachment behaviour of earlier incoming nodes with the goal of interpolating the signal value. We study the non-convexity of the problem at hand, derive conditions when it can be marginally convexified, and propose an alternating projected descent approach between estimating the attachment probabilities and the edge weights. Numerical experiments with synthetic and real data dealing in cold start collaborative filtering corroborate our findings.

  Access Paper or Ask Questions

Fair ranking: a critical review, challenges, and future directions

Jan 29, 2022
Gourab K Patro, Lorenzo Porcaro, Laura Mitchell, Qiuyue Zhang, Meike Zehlike, Nikhil Garg

Ranking, recommendation, and retrieval systems are widely used in online platforms and other societal systems, including e-commerce, media-streaming, admissions, gig platforms, and hiring. In the recent past, a large "fair ranking" research literature has been developed around making these systems fair to the individuals, providers, or content that are being ranked. Most of this literature defines fairness for a single instance of retrieval, or as a simple additive notion for multiple instances of retrievals over time. This work provides a critical overview of this literature, detailing the often context-specific concerns that such an approach misses: the gap between high ranking placements and true provider utility, spillovers and compounding effects over time, induced strategic incentives, and the effect of statistical uncertainty. We then provide a path forward for a more holistic and impact-oriented fair ranking research agenda, including methodological lessons from other fields and the role of the broader stakeholder community in overcoming data bottlenecks and designing effective regulatory environments.

  Access Paper or Ask Questions

An IIoT machine model for achieving consistency in product quality in manufacturing plants

Sep 27, 2021
Abhik Banerjee, Abdur Rahim Mohammad Forkan, Dimitrios Georgakopoulos, Josip Karabotic Milovac, Prem Prakash Jayaraman

Consistency in product quality is of critical importance in manufacturing. However, achieving a target product quality typically involves balancing a large number of manufacturing attributes. Existing manufacturing practices for dealing with such complexity are driven largely based on human knowledge and experience. The prevalence of manual intervention makes it difficult to perfect manufacturing practices, underscoring the need for a data-driven solution. In this paper, we present an Industrial Internet of Things (IIoT) machine model which enables effective monitoring and control of plant machinery so as to achieve consistency in product quality. We present algorithms that can provide product quality prediction during production, and provide recommendations for machine control. Subsequently, we perform an experimental evaluation of the proposed solution using real data captured from a food processing plant. We show that the proposed algorithms can be used to predict product quality with a high degree of accuracy, thereby enabling effective production monitoring and control.

* 10 pages, 8 figures 

  Access Paper or Ask Questions

Topic Model Robustness to Automatic Speech Recognition Errors in Podcast Transcripts

Sep 25, 2021
Raluca Alexandra Fetic, Mikkel Jordahn, Lucas Chaves Lima, Rasmus Arpe Fogh Egebæk, Martin Carsten Nielsen, Benjamin Biering, Lars Kai Hansen

For a multilingual podcast streaming service, it is critical to be able to deliver relevant content to all users independent of language. Podcast content relevance is conventionally determined using various metadata sources. However, with the increasing quality of speech recognition in many languages, utilizing automatic transcriptions to provide better content recommendations becomes possible. In this work, we explore the robustness of a Latent Dirichlet Allocation topic model when applied to transcripts created by an automatic speech recognition engine. Specifically, we explore how increasing transcription noise influences topics obtained from transcriptions in Danish; a low resource language. First, we observe a baseline of cosine similarity scores between topic embeddings from automatic transcriptions and the descriptions of the podcasts written by the podcast creators. We then observe how the cosine similarities decrease as transcription noise increases and conclude that even when automatic speech recognition transcripts are erroneous, it is still possible to obtain high-quality topic embeddings from the transcriptions.

  Access Paper or Ask Questions

Powering Comparative Classification with Sentiment Analysis via Domain Adaptive Knowledge Transfer

Sep 07, 2021
Zeyu Li, Yilong Qin, Zihan Liu, Wei Wang

We study Comparative Preference Classification (CPC) which aims at predicting whether a preference comparison exists between two entities in a given sentence and, if so, which entity is preferred over the other. High-quality CPC models can significantly benefit applications such as comparative question answering and review-based recommendations. Among the existing approaches, non-deep learning methods suffer from inferior performances. The state-of-the-art graph neural network-based ED-GAT (Ma et al., 2020) only considers syntactic information while ignoring the critical semantic relations and the sentiments to the compared entities. We proposed sentiment Analysis Enhanced COmparative Network (SAECON) which improves CPC ac-curacy with a sentiment analyzer that learns sentiments to individual entities via domain adaptive knowledge transfer. Experiments on the CompSent-19 (Panchenko et al., 2019) dataset present a significant improvement on the F1 scores over the best existing CPC approaches.

* 13 pages; EMNLP-2021 Main Conference 

  Access Paper or Ask Questions

Fairness and Discrimination in Information Access Systems

May 12, 2021
Michael D. Ekstrand, Anubrata Das, Robin Burke, Fernando Diaz

Recommendation, information retrieval, and other information access systems pose unique challenges for investigating and applying the fairness and non-discrimination concepts that have been developed for studying other machine learning systems. While fair information access shares many commonalities with fair classification, the multistakeholder nature of information access applications, the rank-based problem setting, the centrality of personalization in many cases, and the role of user response complicate the problem of identifying precisely what types and operationalizations of fairness may be relevant, let alone measuring or promoting them. In this monograph, we present a taxonomy of the various dimensions of fair information access and survey the literature to date on this new and rapidly-growing topic. We preface this with brief introductions to information access and algorithmic fairness, to facilitate use of this work by scholars with experience in one (or neither) of these fields who wish to learn about their intersection. We conclude with several open problems in fair information access, along with some suggestions for how to approach research in this space.

* Currently under review. Please send comments to the authors 

  Access Paper or Ask Questions

Fine-tuning Pre-trained Contextual Embeddings for Citation Content Analysis in Scholarly Publication

Sep 12, 2020
Haihua Chen, Huyen Nguyen

Citation function and citation sentiment are two essential aspects of citation content analysis (CCA), which are useful for influence analysis, the recommendation of scientific publications. However, existing studies are mostly traditional machine learning methods, although deep learning techniques have also been explored, the improvement of the performance seems not significant due to insufficient training data, which brings difficulties to applications. In this paper, we propose to fine-tune pre-trained contextual embeddings ULMFiT, BERT, and XLNet for the task. Experiments on three public datasets show that our strategy outperforms all the baselines in terms of the F1 score. For citation function identification, the XLNet model achieves 87.2%, 86.90%, and 81.6% on DFKI, UMICH, and TKDE2019 datasets respectively, while it achieves 91.72% and 91.56% on DFKI and UMICH in term of citation sentiment identification. Our method can be used to enhance the influence analysis of scholars and scholarly publications.

* 1 figure and three tables 

  Access Paper or Ask Questions