Title
Topic
-
‘An Optimized Acidic Digestion for the Isolation of Microplastics From Biota-Rich Samples’
“Plastic pollution is a growing concern. To analyze plastics in environmental samples, plastics need to be isolated. We present an acidic/oxidative method optimized to preserve plastics while digesting synthetic cellulose acetate and a range of organics encountered in environmental samples.” Find the paper and the full list of authors in Environmental Pollution.
-
‘Generative Adversarial Symmetry Discovery’
“Despite the success of equivariant neural networks in scientific applications, they require knowing the symmetry group a priori. However, it may be difficult to know which symmetry to use as an inductive bias in practice. Enforcing the wrong symmetry could even hurt the performance. In this paper, we propose a framework, LieGAN, to automatically discover equivariances from a dataset using a paradigm akin to generative adversarial training.” Read the paper and see the full list of authors in ArXiv.
-
‘One-Shot Empirical Privacy Estimation for Federated Learning’
“Privacy estimation techniques for differentially private (DP) algorithms are useful for comparing against analytical bounds, or to empirically measure privacy loss in settings where known analytical bounds are not tight. … In this work, we present a novel “one-shot” approach that can systematically address these challenges, allowing efficient auditing or estimation of the privacy loss of a model during the same, single training run used to fit model parameters, and without requiring any a priori knowledge about the model architecture or task.” Read the paper and see the full list of authors in ArXiv.
-
Byron Wallace named Sy and Laurie Sternberg Interdisciplinary Associate Professor for work on machine learning
“Professor Byron Wallace ‘has been awarded Northeastern’s Sy and Laurie Sternberg Interdisciplinary Associate Professorship for his work’ on applying machine learning and natural language processing to healthcare.” In an interview, Wallace gave one example of these applications: “the evolution of NLP systems [means they] can now spit out very plausible text, which medical practitioners can use to synthesize medical evidence and make better decisions for patient treatment.”
-
DeSteno podcast ‘How God Works’ is Ambie finalist
Professor of psychology David DeSteno’s podcast “How God Works” was a finalist for “Best Personal Growth/Spirituality Podcast” in the Ambies, the top awards show in the podcast industry. “How God Works” interrogates why, despite the fact that “religion and science often seem at odds, there’s one thing they can agree on: people who take part in spiritual practices tend to live longer, healthier, and happier lives.” The Ambies award show took place on March 7.
-
Reasoning through the picture: Machine learning between words and images
Researchers have identified a new “cross-modal retrieval” method to operate between “language and vision domains.” From their abstract: “To address this issue, we introduce an intuitive and interpretable model to learn a common embedding space for alignments between images and text descriptions. Specifically, our model first incorporates the semantic relationship information into visual and textual features by performing region or word relationship reasoning.” Read “Image-Text Embedding Learning via Visual and Textual Semantic Reasoning” and see the full list of authors in the IEEE Transactions on Pattern Analysis and Machine Intelligence.
-
‘Dissociation Between Linguistic and Nonlinguistic Statistical Learning in Children With Autism’
“Statistical learning (SL), the ability to detect and extract regularities from inputs, is considered a domain-general building block for typical language development. We compared 55 verbal children with autism (ASD, 6–12 years) and 50 typically-developing children in four SL tasks. The ASD group exhibited reduced learning in the linguistic SL tasks (syllable and letter), but showed intact learning for the nonlinguistic SL tasks (tone and image).” Read the paper and see the full list of authors in the Journal of Autism and Developmental Disorders.
-
‘Backdoor Attacks in Peer-to-Peer Federated Learning’
“We study backdoor attacks in peer-to-peer federated learning systems on different graph topologies and datasets. We show that only 5% attacker nodes are sufficient to perform a backdoor attack with 42% attack success without decreasing the accuracy on clean data by more than 2%. We also demonstrate that the attack can be amplified by the attacker crashing a small number of nodes.” Read the paper and see the full list of authors in ArXiv.
-
‘Stochastic Minimum Vertex Cover in General Graphs: A 3/2-Approximation’
“Our main result is designing an algorithm that returns a vertex cover of G* with size at most (3/2+ϵ) times the expected size of the minimum vertex cover, using only O(n/ϵp) non-adaptive queries. This improves over the best-known 2-approximation algorithm by Behnezhad, Blum, and Derakhshan [SODA’22], who also show that Ω(n/p) queries are necessary to achieve any constant approximation.” Read the paper and see the full list of authors in ArXiv.
-
‘A Closed-Form Solution of the Smoke Filling Time and Descent History in Enclosure Growing Fires With Floor Leaks’
“For the smoke filling time or smoke descent history in enclosure fires with floor leaks, the existing close-formed solutions are all based on the hypothesis that the expansion term is negligible. However, when the smoke interface is near to the floor level, the expansion term is more important than the plume entrainment term and the existing solutions give unrealistic predictions.” Read the paper and see the full list of authors in Fire Technology.
-
‘From Robustness to Privacy and Back’
“We study the relationship between two desiderata of algorithms in statistical inference and machine learning: differential privacy and robustness to adversarial data corruptions. … Dwork and Lei (STOC 2009) … observed that private algorithms satisfy robustness, and gave a general method for converting robust algorithms to private ones. However, all general methods for transforming robust algorithms into private ones lead to suboptimal error rates. Our work gives the first black-box transformation that converts any adversarially robust algorithm into one that satisfies pure differential privacy.” Read the paper and see the full list of authors in ArXiv.
-
Northeastern professors win 2023 Acorn Innovation Awards, helping bring research to market
“Electrical and computer engineering assistant professor Sarah Ostadabbas, professor Deniz Erdogmus and mechanical and industrial engineering associate professor Yi Zheng received MassVentures Acorn Innovation Awards to assist them in testing the viability of their technologies and potentially bringing their research to market.”
-
Sharifkhani receives Riesman Professorship to study ‘macroeconomic risks’ on local labor markets
Assistant professor of finance Ali Sharifkhani has received the Riesman Professorship in the D’Amore-McKim School of Business. Sharifkhani will use the professorship to “study the effects of a firm’s local labor market on its exposure to macroeconomic risks and the expected return on its equity.”
-
Liu receives Walsh Professorship to study ‘diversity faultlines’ in business leadership
Associate professor of accounting Kelvin Liu has received the Walsh Professorship from the D’Amore-McKim School of Business. He will use the professorship to “study the effect of diversity faultlines among senior executives on internal governance and corporate destabilization,” the school of business wrote.
-
‘Effects of Inhaled Cannabis High in Δ9-THC or CBD on the Aging Brain: A Translational MRI and Behavioral Study’
“To understand the neurobiological effects of cannabis on the aging brain, 19–20 months old mice were divided into three groups exposed to vaporized cannabis containing. … Voxel based morphometry, diffusion weighted imaging, and resting state functional connectivity data were gathered after 28 days of exposure and following a two-week washout period. … Chronic inhaled CBD resulted in enhanced global network connectivity that persisted after drug cessation. The behavioral consequences of this sustained change in brain connectivity remain to be determined.” Read the paper and see the full list of authors in Frontiers in Aging Neuroscience.
-
Reframing disability as ‘a property of both humans and machines’
Laura Forlano, professor of art and design and communication studies, has a new article titled “Living Intimately with Machines: Can AI Be Disabled?” Forlano proposes to take seriously the idea that we can “understand disability to be a property of both humans and machines.”
-
‘Do Multi-Document Summarization Models Synthesize?’
“Multi-document summarization entails producing concise synopses of collections of inputs. For some applications, the synopsis should accurately synthesize inputs with respect to a key property or aspect. … In this paper we ask: To what extent do modern multi-document summarization models implicitly perform this type of synthesis? To assess this we perform a suite of experiments that probe the degree to which conditional generation models trained for summarization using standard methods yield outputs that appropriately synthesize inputs.” Read the paper and see the full list of authors in ArXiv.
-
Foregrounding care in the co-creation of urban spaces: How to find ‘liveable urban futures’
This article asks, “Can participatory engagements in the form of more-than-human co-creation be a generative form of socially and ecologically-just and critical urban placemaking?” It goes on to explore “three interrelated examples of critical urban placemaking in the arts, interrogating how we might design for liveable urban futures as matters of care.” In foregrounding care, the authors explore “co-creation” practices that are “responsive and dynamic rather than prescriptive… [and that] “can transform the status quo, rather than merely reproduce it.” Read “Care-full co-curation: critical urban placemaking for more-than-human futures” and see the full list of authors in City: Analysis of Urban Change,…
-
‘Explaining Dataset Changes for Semantic Data Versioning with Explain-Da-V (Technical Report)’
“In multi-user environments in which data science and analysis is collaborative, multiple versions of the same datasets are generated. While managing and storing data versions has received some attention in the research literature, the semantic nature of such changes has remained under-explored. In this work, we introduce \texttt{Explain-Da-V}, a framework aiming to explain changes between two given dataset versions.” Read the paper and see the full list of authors in ArXiv.
-
‘Thought Bubbles: A Proxy into Players’ Mental Model Development’
“Studying mental models has recently received more attention, aiming to understand the cognitive aspects of human-computer interaction. However, there is not enough research on the elicitation of mental models in complex dynamic systems. We present Thought Bubbles as an approach for eliciting mental models and an avenue for understanding players’ mental model development in interactive virtual environments.” Read the paper and see the full list of authors at ArXiv.
-
‘A Bias-Variance-Privacy Trilemma for Statistical Estimation’
“The canonical algorithm for differentially private mean estimation is to first clip the samples to a bounded range and then add noise to their empirical mean. Clipping controls the sensitivity and, hence, the variance of the noise that we add for privacy. But clipping also introduces statistical bias. We prove that this tradeoff is inherent: no algorithm can simultaneously have low bias, low variance, and low privacy loss for arbitrary distributions.” Read the paper and see the full list of authors in ArXiv.
-
‘Making Reconstruction-Based Method Great Again for Video Anomaly Detection’
“Anomaly detection in videos is a significant yet challenging problem. Previous approaches based on deep neural networks employ either reconstruction-based or prediction-based approaches. … existing reconstruction-based methods 1) rely on old-fashioned convolutional autoencoders and are poor at modeling temporal dependency; 2) are prone to overfit the training samples, leading to indistinguishable reconstruction errors. … To address such issues, firstly, we get inspiration from transformer and propose Spatio-Temporal Auto-Trans-Encoder, dubbed as STATE, as a new autoencoder model for enhanced consecutive frame reconstruction.” Find the paper and the full list of authors in ArXiv.
-
Re-evaluating ESG reporting: The missing human factor
Researchers from the Center for the Future of Higher Education and Talent Strategy have produced a new report that details the importance of human capital and its measurement in Environmental, Social, and Governance reporting.
-
Saksono and Hoffman win Google Health Equity Research Initiative award
Assistant professor of health sciences Herman Saksono and professor of applied psychology Jessica Hoffman have won a Google Health Equity Research Initiative award. Their proposal, “Augmenting fitness tracking data with community storytelling to advance the impact of wearables in promoting health equity,” hopes to interrogate “how to amplify social support in marginalized communities by augmenting fitness data with first-person storytelling,” they wrote. They plan to leverage fitness tracking devices to “facilitate social support within marginalized communities.” Crucially, this study is a product of a close community partnership with the Mattapan Food and Fitness Coalition, which was established in 2017.
-
‘Trajectory-Aware Eligibility Traces for Off-Policy Reinforcement Learning’
“Off-policy learning from multistep returns is crucial for sample-efficient reinforcement learning, but counteracting off-policy bias without exacerbating variance is challenging. Classically, off-policy bias is corrected in a per-decision manner. … Many off-policy algorithms rely on this mechanism, along with differing protocols for cutting the IS ratios to combat the variance of the IS estimator. Unfortunately, once a trace has been fully cut, the effect cannot be reversed. … In this paper, we propose a multistep operator that can express both per-decision and trajectory-aware methods.” Read the paper and see the full list of authors in ArXiv.