Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Scallop – A Language for Neurosymbolic Programming

scallop-lang.org

Post reply on HN
Print view View original

51–60 of 68 posts

Re: Scallop – A Language for Neurosymbolic Programming

#51

Post by daveguy »

versteegen wrote: post #15

Wow, I'm currently reading the Scallop paper, so funny to see it posted here! I really love the concept. This isn't just differentiable neurosymbolic declarative probabilistic programming; Scallop has the flexibility of letting you use various (18 included) or custom provenance semirings to e.g. track "proofs" why a relational fact holds, not just assign it a probability. Sounds cool but I'm still trying to figure ou…

I'm pretty sure "differentiable" isn't necessary or sufficient to create valid and useful code.

Re: Scallop – A Language for Neurosymbolic Programming

#52

Post by nextos »

xabush wrote: post #44

How does Scallop scale on large knowledge bases (KBs) for doing probabilistic reasoning? I'm currently working on large KB with ~ 12M facts and trying to do probabilistic inference on it. So far I've been using [cplint]( https://friguzzi.github.io/cplint/_build/html/index.html ) which is based on SWI-Prolog. It works fine for toy examples, however, it doesn't finish running for the large KB - even after waiting for i…

ProbLog? https://dtai.cs.kuleuven.be/problog

Re: Scallop – A Language for Neurosymbolic Programming

#53

Post by adastra22 »

daveguy wrote: post #51
versteegen wrote: post #15

Wow, I'm currently reading the Scallop paper, so funny to see it posted here! I really love the concept. This isn't just differentiable neurosymbolic declarative probabilistic programming; Scallop has the flexibility of letting you use various (18 included) or custom provenance semirings to e.g. track "proofs" why a relational fact holds, not just assign it a probability. Sounds cool but I'm still trying to figure ou…

I'm pretty sure "differentiable" isn't necessary or sufficient to create valid and useful code.

On the one hand, there are problems which by accident or design are nondifferentiable. Cryptography, for example.

In the other hand, these problems are routinely analyzed and solved by differentiable algorithms running on neural net substrates (e.g. you).

Re: Scallop – A Language for Neurosymbolic Programming

#54

Post by adastra22 »

FloorEgg wrote: post #2

Ever since I learned about category theory and its relationship with symbolic reasoning I've suspected that AGI will come from elegantly combining symbolic reasoning and probabilistic reasoning. This is the first project I've seen that seems to be positioned that way. Very cool.

There is a long history of efforts to combine symbolic and connectionist approaches. This is hardly the first!

Re: Scallop – A Language for Neurosymbolic Programming

#55

Post by daveguy »

adastra22 wrote: post #53
daveguy wrote: post #51

Earlier quoted context omitted.

I'm pretty sure "differentiable" isn't necessary or sufficient to create valid and useful code.

On the one hand, there are problems which by accident or design are nondifferentiable. Cryptography, for example. In the other hand, these problems are routinely analyzed and solved by differentiable algorithms running on neural net substrates (e.g. you).

Nah, I'm not crackin crypto with my noggin buddy. Sorry.

Re: Scallop – A Language for Neurosymbolic Programming

#56

Post by riku_iki »

xabush wrote: post #44

How does Scallop scale on large knowledge bases (KBs) for doing probabilistic reasoning? I'm currently working on large KB with ~ 12M facts and trying to do probabilistic inference on it. So far I've been using [cplint]( https://friguzzi.github.io/cplint/_build/html/index.html ) which is based on SWI-Prolog. It works fine for toy examples, however, it doesn't finish running for the large KB - even after waiting for i…

I am surprised you have problems with 12M facts and can't process them in a week, looks like bug in software you are using.

Re: Scallop – A Language for Neurosymbolic Programming

#57

Post by light_hue_1 »

mentalgear wrote: post #45
light_hue_1 wrote: post #31

The problem with scallop is that no one has ever shown a single program that wasn't easier to write without it. Their papers usually contain also no examples, and the ones that do are a heck of a lot more complicated than asking the model to do it directly. The programming languages world let's them get away with this because they're excited to be relevant in the LLM universe. But I wouldn't accept any of this work i…

I think you misunderstand what a neuro-symbolic programming language (like Scallop) is for. It's not about performance, but safety. Making safe decisions becomes exponentially more important as ML / agents evolve, to avoid "performant" but ultimately inefficient/dangerous/wasteful inferences.

Then show me programs that meaningfully improves safety. And compare them to baseline options to demonstrate this. None of these examples improve safety beyond a trivial check on the output which I can also do with a simple prompt.

Re: Scallop – A Language for Neurosymbolic Programming

#58

Post by adastra22 »

daveguy wrote: post #55
adastra22 wrote: post #53

Earlier quoted context omitted.

On the one hand, there are problems which by accident or design are nondifferentiable. Cryptography, for example. In the other hand, these problems are routinely analyzed and solved by differentiable algorithms running on neural net substrates (e.g. you).

Nah, I'm not crackin crypto with my noggin buddy. Sorry.

That's not what I was saying?

Re: Scallop – A Language for Neurosymbolic Programming

#59

Post by sitkack »

versteegen wrote: post #15

Wow, I'm currently reading the Scallop paper, so funny to see it posted here! I really love the concept. This isn't just differentiable neurosymbolic declarative probabilistic programming; Scallop has the flexibility of letting you use various (18 included) or custom provenance semirings to e.g. track "proofs" why a relational fact holds, not just assign it a probability. Sounds cool but I'm still trying to figure ou…

Papers are linked here https://www.scallop-lang.org/resources.html

https://www.cis.upenn.edu/~mhnaik/papers/neurips21.pdf

https://dl.acm.org/doi/10.1145/3591280

There is a 135 page book on Scallop https://www.cis.upenn.edu/~mhnaik/papers/fntpl24.pdf

Re: Scallop – A Language for Neurosymbolic Programming

#60

Post by sitkack »

suddenlybananas wrote: post #35
mountainriver wrote: post #34

Earlier quoted context omitted.

Yes, this seems to be what the symbolists always forget. We don’t use symbolism like this, we just have very dense neural connections that emerge from scale and approximate it

That's not really what symbolists actually argue. Read Fodor and Pylylshyn 1988 to better understand how symbolists view the relationship between symbolic representation and connectionist models. What you're saying is akin to saying there's no point in doing neuroscience or trying to understand neural-networks as its just particle physics deep down.

Connectionism and cognitive architecture: A critical analysis https://www.semanticscholar.org/paper/Connectionism-and-cogn...

Fodor and Pylyshyn's Critique of Connectionism and the Brain as Basis of the Mind https://arxiv.org/abs/2307.14736

Post reply on HN