[HN Gopher] Time Series Forecasting with Graph Transformers
___________________________________________________________________
Time Series Forecasting with Graph Transformers
Author : turntable_pride
Score : 118 points
Date : 2025-06-17 18:05 UTC (1 days ago)
(HTM) web link (kumo.ai)
(TXT) w3m dump (kumo.ai)
| ziofill wrote:
| I can't stand websites that override scrolling
| pealco wrote:
| Most of my time interacting with this site was spent in
| developer tools, trying to figure out where the scrolling
| behavior was coming from. (Couldn't figure it out.) I can't
| understand why people are still doing this in 2025.
| almosthere wrote:
| Most likely the developer is using a Windows computer.
| bestest wrote:
| Enter this in the console:
|
| document.body.onwheel = (e) => e.stopPropagation();
| rossant wrote:
| I came here to say this. Don't mess with my scrollbar. Ever.
| monkeydust wrote:
| wow didn't realize that until I saw this comment, now I cant
| unrealize it and angry
| cwmoore wrote:
| "Here, sign this." accept all cookies
| cye131 wrote:
| I'm not a fan of this blog post as it tries to pass off a method
| that's not accepted as a good or standard time series methodology
| (graph transformers) as though it were a norm. Transformers
| perform poorly on time series, and graph deep learning performs
| poorly for tasks that don't have real behaviorial/physical edges
| (physical space/molecules/social graphs etc), so it's unclear why
| combining them would produce anything useful for "business
| applications" of time series like sales forecasting.
|
| For those interested in transformers with time series, I
| recommend reading this paper: https://arxiv.org/pdf/2205.13504.
| There is also plenty of other research showing that transformers-
| based time series models generally underperform much simpler
| alternatives like boosted trees.
|
| After looking further it seems like this startup is both trying
| to publish academic research promoting these models as well as
| selling it to businesses, which seems like a conflict of interest
| to me.
| tough wrote:
| thoughts on TimesFM?
|
| > After looking further it seems like this startup is both
| trying to publish academic research promoting these models as
| well as selling it to businesses, which seems like a conflict
| of interest to me.
|
| is this a general rule of thumb that one should not use the
| same organization to publish research and pursue
| commercialization generally?
| orochimaaru wrote:
| Not really. There is no rule against it. You can have a team
| that research, publishes, patents and shares the patents with
| commercial scalers. It's easier with ML than with
| manufacturing.
| shirokiba wrote:
| Would you be so kind as to recommend some resources on modern,
| promising methods for time series forecasting? I'm starting a
| position doing this work soon and would like to learn more
| about it if you'd be willing to share
| srean wrote:
| Read all the M series of competitions and the papers that
| come out of those exercises. Read Keogh. Also have a healthy
| respect and understanding of the traditional methods rather
| than getting distracted by all that happens to be _shiny_
| now.
| lamename wrote:
| Wow a sane person among all the hype. Great to see you!
| srean wrote:
| Lol. Yeah, the hype train blinds.
| ethan_smith wrote:
| Recent work like Informer (AAAI'21) and Autoformer (NeurIPS'21)
| have shown competitive performance against statistical methods
| by addressing the quadratic complexity and long-range
| dependency issues that plagued earlier transformer
| architectures for time series tasks.
| rusty1s wrote:
| Hey, one of the authors here--happy to clarify a few things.
|
| > Transformers perform poorly on time series.
|
| That's not quite the point of our work. The model isn't about
| using Transformers for time series per se. Rather, the focus is
| on how to enrich forecasting models by combining historical
| sequence data with external information, which is often
| naturally structured as a graph. This approach enables the
| model to flexibly incorporate a wide range of useful signals,
| such as:
|
| * Weather forecasts for a region
|
| * Sales from similar products or related categories
|
| * Data from nearby locations or stations
|
| * More fine-granular recent interactions/activities
|
| * Price changes and promotional campaigns
|
| * Competitor data (e.g., pricing, availability)
|
| * Aggregated regional or market-level statistics
|
| The architecture is modular: we don't default to a Transformer
| for the past sequence component (and in fact use a simpler
| architecture). The Graph Transformer/Graph Neural Network then
| extends the past sequence component by aggregating from
| additional sources.
|
| > It seems like this startup is both trying to publish academic
| research promoting these models as well as selling it to
| businesses which seems like a conflict of interest to me.
|
| That's a bold claim. All of our academic work is conducted in
| collaboration with university partners, is peer-reviewed, and
| has been accepted at top-tier conferences. Sharing blog posts
| that explain the design decisions behind our models isn't a
| conflict of interest--it's part of making our internals more
| transparent.
| fumeux_fume wrote:
| Lol, a bold claim. It's a rational assumption that any
| business publishing "academic work" is selling you the upside
| while omitting or downplaying the downside.
| ayongpm wrote:
| https://dontfuckwithscroll.com/
| rusty1s wrote:
| Forwarded :)
___________________________________________________________________
(page generated 2025-06-18 23:02 UTC)