--- title: "Kilian Q. Weinberger — author profile and papers" description: "Kilian Q. Weinberger, Cornell University: 2 papers on Elamur Research (2018–2020), h-index 72 — affiliations, topics, co-authors and who cites them in…" canonical: "https://research.elamur.ai/free/en/authors/kilian-q-weinberger/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/kilian-q-weinberger/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Kilian Q. Weinberger # Kilian Q. Weinberger Kilian Q. Weinberger's papers here apply machine learning to natural language processing, mostly to the problem of training neural text models when labelled examples are scarce. One strand asks how a classifier built on annotated English text can be carried over to languages that have only unlabelled text, which ties the work to [Sentiment & emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) and [Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/). Another strand looks at why adapting large pre-trained models to small datasets so often fails, and at which simple changes to the training procedure make it dependable. The two papers in our library are both widely cited. [Adversarial Deep Averaging Networks for Cross-Lingual Sentiment Classification](https://md.research.elamur.ai/free/en/papers/chen-2018-adversarial-deep-averaging-networks-cross/) (2018) introduces ADAN. In this model a shared feature extractor serves both a sentiment classifier and an adversarial discriminator that tries to identify the input's language. The learned features are pushed to keep sentiment information while hiding which language the text came from. Instead of a gradient reversal layer, the method aligns the two feature distributions through a Wasserstein distance, which steadies training. The more recent [Revisiting Few-sample BERT Fine-tuning](https://md.research.elamur.ai/free/en/papers/zhang-2020-revisiting-few-sample-bert-fine/) (2020) turns to pre-trained transformers. It traces the erratic, seed-dependent results of fine-tuning BERT on small GLUE tasks to three common habits: an optimizer that omits Adam's bias correction, reuse of the topmost pre-trained layers, and short fixed training schedules. It then tests a remedy for each. Weinberger is at [Cornell University](https://md.research.elamur.ai/free/en/universities/cornell-university/). Earlier bylines list [Washington University in St. Louis](https://md.research.elamur.ai/free/en/universities/washington-university-in-st-louis/), as well as [Yahoo](https://md.research.elamur.ai/free/en/companies/yahoo/) (United States) and the [University of Pennsylvania](https://md.research.elamur.ai/free/en/universities/university-of-pennsylvania/). Co-authors on these papers include [Xilun Chen](https://md.research.elamur.ai/free/en/authors/xilun-chen/), [Claire Cardie](https://md.research.elamur.ai/free/en/authors/claire-cardie/) and [Tianyi Zhang](https://md.research.elamur.ai/free/en/authors/tianyi-zhang/), along with Felix Wu, Yoav Artzi, Ben Athiwaratkun, Yu Sun and Arzoo Katiyar. Kilian Q. Weinberger has 2 papers in our library, in 2018–2020, most of them on [Sentiment & emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/), [Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/); often with [Arzoo Katiyar](https://md.research.elamur.ai/free/en/authors/arzoo-katiyar/), [Ben Athiwaratkun](https://md.research.elamur.ai/free/en/authors/ben-athiwaratkun/), [Claire Cardie](https://md.research.elamur.ai/free/en/authors/claire-cardie/). 2 papers in our library · 2018–2020 current affiliation [Cornell University](https://md.research.elamur.ai/free/en/universities/cornell-university/) · Ithaca United States [OpenAlex](https://openalex.org/A5006380227) · [ORCID](https://orcid.org/0009-0008-9313-7239) · [Wikidata](https://www.wikidata.org/wiki/Q102449581) · [**h-index 72**](https://openalex.org/authors/A5006380227) · [231 works](https://openalex.org/works?filter=author.id:A5006380227) · [81,851 citations](https://openalex.org/works?filter=author.id:A5006380227&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [2 works in our library](https://md.research.elamur.ai/free/en/authors/kilian-q-weinberger/#papers) · [4,126 citations in our library](https://md.research.elamur.ai/free/en/authors/kilian-q-weinberger/cited-by/) · 4 more works in our library · [⭐ Paper Star rank #2371](https://md.research.elamur.ai/free/en/paper-stars/page/24/#star-2371) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Kilian+Q.+Weinberger) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Kilian+Q.+Weinberger) · [dblp](https://dblp.org/search?q=Kilian+Q.+Weinberger) · [ACL Anthology](https://aclanthology.org/search/?q=Kilian+Q.+Weinberger) ## Affiliations [🎓**Cornell University** Ithaca · United States 2015–2026 · 95 papers*current**employment (Wikidata)*](https://md.research.elamur.ai/free/en/universities/cornell-university/) · [🎓**Washington University in St. Louis** St Louis · United States 2010–2021 · 49 papers](https://md.research.elamur.ai/free/en/universities/washington-university-in-st-louis/) · [🏢**Yahoo** Sunnyvale · United States 2008–2009 · 9 papers](https://md.research.elamur.ai/free/en/companies/yahoo/) · [🎓**University of Pennsylvania** Philadelphia · United States 2004–2007 · 9 papers*education until 2007 (Wikidata)*](https://md.research.elamur.ai/free/en/universities/university-of-pennsylvania/) · [🎓**Tsinghua University** Beijing · China 2018 · 2 papers](https://md.research.elamur.ai/free/en/universities/tsinghua-university/) · [🎓**University of Oxford** Oxford · United Kingdom 1999–2002*education 1999–2002 (Wikidata)*](https://md.research.elamur.ai/free/en/universities/university-of-oxford/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 5 more institutions on single bylines are not listed. ## Topics [Sentiment & emotion 1](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) · [Multilingual & cross-lingual NLP 1](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) ## Works by year ### 2020s [**2020** 1 paper](https://md.research.elamur.ai/free/en/papers/zhang-2020-revisiting-few-sample-bert-fine/) ### 2010s [**2018** 1 paper](https://md.research.elamur.ai/free/en/papers/chen-2018-adversarial-deep-averaging-networks-cross/) ## Papers The most cited first (OpenAlex and our library). 1. **[Adversarial Deep Averaging Networks for Cross-Lingual Sentiment Classification](https://md.research.elamur.ai/free/en/papers/chen-2018-adversarial-deep-averaging-networks-cross/)** *(2018 · 393 citations)* The paper addresses sentiment classification in languages with little or no annotated data. It transfers knowledge from labeled English (SOURCE) texts to a TARGET language that has only unlabeled text. The authors propose ADAN, which feeds a Deep Averaging Network (DAN) feature extractor into two branches: a… 2. **[Revisiting Few-sample BERT Fine-tuning](https://md.research.elamur.ai/free/en/papers/zhang-2020-revisiting-few-sample-bert-fine/)** *(2020 · 361 citations)* Fine-tuning BERT on small datasets is notoriously unreliable. Runs that differ only in random seed can produce very different or even collapsed models, so practitioners often train many restarts and keep the best one. This study traces the instability to three widespread practices. First, BERTADAM, the default… ## Also in our library 4 more works of theirs are in our library without a page here yet; they will appear as we publish them. ## Co-authors here 8 co-authors with a page, the most papers together first. - [Arzoo Katiyar](https://md.research.elamur.ai/free/en/authors/arzoo-katiyar/) - [Ben Athiwaratkun](https://md.research.elamur.ai/free/en/authors/ben-athiwaratkun/) - [Claire Cardie](https://md.research.elamur.ai/free/en/authors/claire-cardie/) - [Felix Wu](https://md.research.elamur.ai/free/en/authors/felix-wu/) - [Tianyi Zhang](https://md.research.elamur.ai/free/en/authors/tianyi-zhang/) - [Xilun Chen](https://md.research.elamur.ai/free/en/authors/xilun-chen/) - [Yoav Artzi](https://md.research.elamur.ai/free/en/authors/yoav-artzi/) - [Yu Sun](https://md.research.elamur.ai/free/en/authors/yu-sun/) ## Cited by Papers of our library cite their works 4,126 times (of the 140,884 papers whose bibliographies we read); [284 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/kilian-q-weinberger/cited-by/).