veganism.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
Veganism Social is a welcoming space on the internet for vegans to connect and engage with the broader decentralized social media community.

Administered by:

Server stats:

293
active users

#RecSys

0 posts0 participants0 posts today
IRRJ<p>Published at <a href="https://sigmoid.social/tags/IRRJ" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>IRRJ</span></a>: "On the challenges of studying bias in Recommender Systems: The effect of data characteristics and algorithm configuration" by Savvina Daniil, Manel Slokom, Mirjam Cuper, Cynthia Liem, Jacco van Ossenbruggen, and Laura Hollink. <a href="https://sigmoid.social/tags/RecSys" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>RecSys</span></a> <a href="https://sigmoid.social/tags/Bias" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Bias</span></a> <a href="https://sigmoid.social/tags/DataSynthesis" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>DataSynthesis</span></a> <a href="https://sigmoid.social/tags/Reproducibility" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Reproducibility</span></a> </p><p><a href="https://doi.org/10.54195/irrj.19607" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">doi.org/10.54195/irrj.19607</span><span class="invisible"></span></a></p>
Michael Ekstrand<p>New at my blog: I'd been bothered for a few years now in teaching <a href="https://hci.social/tags/recsys" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>recsys</span></a> by the need for a biased lift computation for informative product-relatedness measures that aren't dominated by low-information items. So this term, I sat down to solve the problem. <a href="https://md.ekstrandom.net/blog/2025/01/biased-lift" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">md.ekstrandom.net/blog/2025/01</span><span class="invisible">/biased-lift</span></a></p>
Michael Ekstrand<p>Do you appreciate news? Do you want to help <a href="https://hci.social/tags/recsys" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>recsys</span></a> research? POPROX News is open for subscriptions!</p><p>The Platform for OPen Recommendation and Online eXpermentation is an <a href="https://hci.social/tags/NSFfunded" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NSFfunded</span></a> project to help scientists and journalists explore better ways to select and present news stories. Our MVP is a daily personalized newsletter — if you'd like to receive that, and periodic surveys, sign up at <a href="https://user.poprox.ai/enroll?source=ff&amp;subsource=memd" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">user.poprox.ai/enroll?source=f</span><span class="invisible">f&amp;subsource=memd</span></a></p><p>After signup, you'll receive a confirmation email — check spam if needed.</p>
Michael Ekstrand<p><a href="https://hci.social/tags/recsys" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>recsys</span></a> fail: this is the second time — at least — LinkedIn only showed me the post(s) advertising an event I wanted to attend after registration closed.</p>
Michael Ekstrand<p>might have developed a new <a href="https://hci.social/tags/recsys" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>recsys</span></a> hyperparameter search strategy in class last night.</p><p>CalvinSearch: try hyperparameter settings until The Complete Calvin and Hobbes is the top recommendation.</p>
Michael Ekstrand<p>What if <a href="https://hci.social/tags/RecSys" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>RecSys</span></a> put as much energy into explicitly anti-fascist recommendations as it does into viewpoint-diverse recommendations?</p><p>What if the goal isn’t to model tolerance for diversity, but to identify items that will increase the reader’s empathy and understanding of their neighbors and their needs?</p><p>This paper provides some thoughts applicable to that direction. <a href="https://doi.org/10.1108/JD-01-2020-0002" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">doi.org/10.1108/JD-01-2020-000</span><span class="invisible">2</span></a></p>
Deezer Research<p>we will be at <a href="https://sigmoid.social/tags/recsys2024" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>recsys2024</span></a> from monday on! with a set of papers, talks and presentations throughout the week.</p><p><a href="https://www.linkedin.com/posts/deezer-research_deezer-recsys2024-bari-activity-7250525472231436288-dgc8?utm_source=share&amp;utm_medium=member_desktop" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">linkedin.com/posts/deezer-rese</span><span class="invisible">arch_deezer-recsys2024-bari-activity-7250525472231436288-dgc8?utm_source=share&amp;utm_medium=member_desktop</span></a></p><p><a href="https://sigmoid.social/tags/RecSys" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>RecSys</span></a></p>
Michael Ekstrand<p>Looking for another workshop to submit to at <a href="https://hci.social/tags/RecSys2024" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>RecSys2024</span></a>? There are *2 weeks left* to submit to AltRecSys and join us for a discussion on the questions, needs, and opportunities the <a href="https://hci.social/tags/RecSys" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>RecSys</span></a> community is overlooking. Details in the call: <a href="https://altrecsys.github.io/call/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">altrecsys.github.io/call/</span><span class="invisible"></span></a></p>
Michael Ekstrand<p>In case you need another reason to submit to (or just attend) FAccTRec at <a href="https://hci.social/tags/RecSys2024" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>RecSys2024</span></a> — we'll be having a keynote from <span class="h-card" translate="no"><a href="https://recsys.social/@jvinagre" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>jvinagre</span></a></span> on the DSA, AI Act, and <a href="https://hci.social/tags/RecSys" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>RecSys</span></a>. Papers due on Friday! <a href="https://facctrec.github.io/facctrec2024/cfp/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">facctrec.github.io/facctrec202</span><span class="invisible">4/cfp/</span></a></p>
Michael Ekstrand<p>Do GPUs have an equivalent of "cpu-seconds" like getrusage() returns for CPU utilization? If so, how might I obtain it?</p><p>I'm trying to instrument <a href="https://hci.social/tags/recsys" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>recsys</span></a> runs with resource utilization, and I can easily get wall time, CPU time, max resident memory, and max CUDA memory, but GPU time is more elusive right now.</p>
Michael Ekstrand<p>New job opening — we're hiring a research software engineer for our <a href="https://hci.social/tags/recsys" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>recsys</span></a> infrastructure project. Hybrid and remote options available. Apply here: <a href="https://hr.myu.umn.edu/jobs/ext/361124" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">hr.myu.umn.edu/jobs/ext/361124</span><span class="invisible"></span></a></p>
Michael Ekstrand<p>quick academic service update: pleased to join the editorial board of Transactions on <a href="https://hci.social/tags/RecSys" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>RecSys</span></a>: <a href="https://dl.acm.org/journal/tors/editorial-board" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">dl.acm.org/journal/tors/editor</span><span class="invisible">ial-board</span></a></p><p>send your papers!</p>
Michael Ekstrand<p>Super excited to be co-teaching a tutorial at <a href="https://hci.social/tags/RecSys2024" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>RecSys2024</span></a> this year on doing experiments with POPROX, an <a href="https://hci.social/tags/NSFFunded" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NSFFunded</span></a> platform currently in development to support user-facing <a href="https://hci.social/tags/recsys" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>recsys</span></a> experiments. Come join us! <a href="https://recsys.acm.org/recsys24/tutorials/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">recsys.acm.org/recsys24/tutori</span><span class="invisible">als/</span></a></p>
Michael Ekstrand<p>Super excited to be involved with 2 workshops for <a href="https://hci.social/tags/RecSys2024" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>RecSys2024</span></a>. <span class="h-card" translate="no"><a href="https://recsys.social/@FAccTRec" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>FAccTRec</span></a></span> is returning for a 7th year (it's been that long already?), and <span class="h-card" translate="no"><a href="https://recsys.social/@alansaid" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>alansaid</span></a></span>, Sole Pera, and I are organizing a brand-new workshop&nbsp;— the AltRecSys Workshop on Alternative, Unexpected, and Critical Work on Recommendation.</p><p>Details on both to come. Plan to join us for an exciting discussion of what gets overlooked in <a href="https://hci.social/tags/RecSys" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>RecSys</span></a> research!</p>
Michael Ekstrand<p>In the main track poster session, we have a poster for work led by my recently-graduated PhD Ngozi Ihemelandu on multiple comparisons in IR evaluation at <a href="https://hci.social/tags/recsys" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>recsys</span></a> scale. We recommend using Benjamini-Yekuteili, or Bonferoni if sample size is huge &amp; the simplicity is preferred. <a href="https://md.ekstrandom.net/pubs/ecir-mcp" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">md.ekstrandom.net/pubs/ecir-mc</span><span class="invisible">p</span></a></p>
Michael Ekstrand<p>Elementary S4E2: creepiest <a href="https://hci.social/tags/recsys" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>recsys</span></a> ever.</p><p>I don’t think we’ll be implementing it in POPROX.</p>
Michael Ekstrand<p>Amifa Raj also has a dissertation chapter —&nbsp;her work on grid-aware fairness-enhancing reranking to improve the fairness of grid-based <a href="https://hci.social/tags/search" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>search</span></a> and <a href="https://hci.social/tags/recsys" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>recsys</span></a> result layouts will be in the IR for Good track: <a href="https://md.ekstrandom.net/pubs/ecir-fair-grids" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">md.ekstrandom.net/pubs/ecir-fa</span><span class="invisible">ir-grids</span></a></p>
Michael Ekstrand<p>This one is led by my student Ngozi Ihemelandu, and is the last piece of her dissertation that she defended this week. It looks at multiple-comparison corrections and assesses their performance for search and especially <a href="https://hci.social/tags/recsys" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>recsys</span></a> experiments. TL;DR using Benjamini-Yekutieli instead of Bonferonni is a good default. <a href="https://md.ekstrandom.net/pubs/ecir-mcp" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">md.ekstrandom.net/pubs/ecir-mc</span><span class="invisible">p</span></a></p>
Michael Ekstrand<p>He also touches on <a href="https://hci.social/tags/recsys" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>recsys</span></a> and advertising: ‘Moreover, from the digital footprints spread throughout the Internet, technologies …[can] control mental and relational habits for commercial or political purposes, often without our knowledge, thus limiting our conscious exercise of freedom of choice. In a space like the Web, marked by information overload, they can structure the flow of data according to criteria of selection that are not always perceived by the user.’</p>
Davide Eynard (+mala)<p>Hi everyone! Six more months passed since my last <a href="https://fosstodon.org/tags/introduction" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>introduction</span></a>, so here is an updated one:</p><p>AKA: +mala, AiTTaLaM</p><p>Job: Doin’ trustworthy <a href="https://fosstodon.org/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a> @ moz://a.ai - more generally I love <a href="https://fosstodon.org/tags/teaching" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>teaching</span></a>, no matter if to humans or machines :-)</p><p>Projects: 3564020356.org is the oldest (~22yrs 😅), <a href="https://fosstodon.org/tags/PicoGopher" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>PicoGopher</span></a> the most recent... Look around and find the rest! 😜</p><p>Interests: <a href="https://fosstodon.org/tags/bouldering" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>bouldering</span></a> <a href="https://fosstodon.org/tags/gopher" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>gopher</span></a> <a href="https://fosstodon.org/tags/SelfHosting" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>SelfHosting</span></a> <a href="https://fosstodon.org/tags/opensource" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>opensource</span></a> <a href="https://fosstodon.org/tags/reversing" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>reversing</span></a> <a href="https://fosstodon.org/tags/fediverse" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>fediverse</span></a> <a href="https://fosstodon.org/tags/recsys" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>recsys</span></a> <a href="https://fosstodon.org/tags/ML" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ML</span></a> <a href="https://fosstodon.org/tags/solarpunk" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>solarpunk</span></a> <a href="https://fosstodon.org/tags/CommunitiesOfExperience" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>CommunitiesOfExperience</span></a></p>